@takeokunn/metabase-mcp

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v1.2.0
Disambiguation2/5
With 429 tools, there is significant overlap and many similar tool names (e.g., numerous get_, export_, and execute_ variants). While descriptions help, the sheer volume makes it difficult for an agent to distinguish between closely related tools, especially for embedding and public sharing operations.
Naming Consistency3/5
The naming pattern is predominantly verb_noun (e.g., create_card, delete_user), which is good. However, there are inconsistencies: some tools use 'list_' vs 'get_' (compare list_collections vs get_collection), and there are redundant variations like 'export_dashcard_query' and 'export_dashboard_card_query'. Overall, the pattern is recognizable but not perfectly uniform.
Tool Count1/5
429 tools is an extreme number for a single MCP server. This overwhelms the agent's context and selection process. Even if the server aims to cover the entire Metabase API, the count is impractical and likely exceeds the reasonable scope for coherent tool organization.
Completeness3/5
The server covers a wide range of Metabase entities (cards, dashboards, collections, permissions, embedding, etc.), but notable gaps exist: missing delete_metric, delete_measure, delete_alert (only delete_alert_subscription), and no delete_pulse. While many CRUD operations are present, some lifecycle actions are absent, leading to a medium completeness score.
Average 2.9/5 across 395 of 429 tools scored. Lowest: 1.8/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 5 commits in the last 12 weeks
- Last stable release on April 10, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as side effects, permissions required, or whether it is destructive. The description merely restates the tool's name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (6 words), but this conciseness sacrifices essential information. It is under-specified for a tool with nested parameters and multiple siblings.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested input object, no output schema, no annotations), the description is completely inadequate. It provides no information on what the action does, what parameters mean, or what the result looks like.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% coverage from the description, meaning the description does not explain any parameters. Although the schema itself has descriptions, the description fails to add meaningful context beyond what's in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the verb 'execute' and resource 'dashcard', but 'action' is vague. It does not distinguish from sibling tools like execute_action or execute_card, which have similar names.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as execute_action or run_dashcard_query. The description provides no context for usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description does not disclose any behavioral traits (e.g., auth requirements, side effects, or return behavior).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words, but it is too brief and lacks important details. Conciseness is good, but completeness suffers.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has many parameters, no output schema, and no annotations, the description is far from complete. An agent would lack understanding of param meanings, return format, and usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the tool description does not explain any of the required parameters (token, dashcard_id, card_id, zoom, x, y). The description adds no value beyond the schema's property names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool gets a map tile for a preview embedded dashboard dashcard, which is specific. However, among many sibling tile tools (e.g., get_basic_tile, get_embed_dashboard_tile), it does not distinguish when to use this specific variant.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, nor any prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description fails to disclose any behavioral traits such as idempotency, side effects, permissions required, or whether it overwrites existing indices.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence: 'Create a new model index in Metabase.' It is concise but omits essential details, making it under-specified rather than efficiently concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested object parameters, no annotations, and no output schema, the description is severely lacking. It does not explain what a model index is, how the parameters work, or what the result is.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the parameters. Schema coverage is 0%, so the description should compensate, but it does not mention pk_ref, model_id, or value_ref.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and the resource 'new model index' in Metabase. It distinguishes itself from sibling tools like get_model_index or delete_model_index, but does not elaborate on what a model index is or its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. There is no mention of conditions, prerequisites, or scenarios where creating a model index is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description does not disclose side effects, permissions, or response behavior. It merely states 'execute' without indicating whether the action mutates state or requires authentication.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, but it is underspecified and fails to provide useful content. True conciseness would pack meaning into few words; here it is vague and uninformative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex context (many sibling tools, no output schema, nested parameters), the description is grossly insufficient. It omits critical details like return values, error conditions, and usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, and the description adds no explanation for parameters (uuid, dashcard_id, parameters). Without additional context, the agent cannot infer what values are expected.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it executes an action on a public dashcard, providing a verb and resource. However, it does not distinguish among sibling tools like execute_dashcard_action or execute_public_action, leaving ambiguity about what 'action' means.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as execute_public_action or get_public_dashcard_execute. The description lacks context on prerequisites or intended scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as side effects, required permissions, or the effect on the cached data. The word 'refresh' implies a nondestructive update, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words, but it is too brief to be fully useful. It could be expanded with context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and the presence of many related siblings, the description is incomplete. It does not explain what happens when the cache is refreshed, whether the card must already be persisted, or what the return value is.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the tool description must compensate but only restates 'card_id' without adding any meaning. It fails to explain the role or expected values of the parameter beyond what the schema already indicates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'refresh' and the resource 'persisted model cache for a card', making the action specific. However, it does not distinguish from sibling tools like 'persist_card' or 'enable_model_persistence', missing an opportunity to differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'persist_card', 'unpersist_card', or 'list_persisted_models'. There is no mention of prerequisites, context, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden but only says 'Create a new dashboard', implying a write operation without disclosing side effects, permissions, or what happens to existing data. No behavioral traits are revealed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but under-informative for a tool with nested parameters. It is too short to adequately describe the tool's functionality and usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, multiple sibling tools, and nested parameters, the description is woefully incomplete. It provides no context about return values, prerequisites, or typical use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not mention any parameters. It fails to add meaning beyond the schema, leaving the agent with no guidance on required inputs like 'name' or optional fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a new dashboard in Metabase', specifying the action and resource. However, it does not differentiate from sibling tools like copy_dashboard or create_dashboard_public_link, missing a distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives, such as when to create vs copy a dashboard, or any prerequisites. The description solely states the basic action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. It only states 'create a new timeline' which implies mutation, but does not disclose permissions, side effects, or response behavior. This is insufficient for a creation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no structure. It is concise but overly brief, lacking any breakdown of functionality or usage context. Every sentence should earn its place, but this one only restates the name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a nested input object, the description is severely incomplete. It fails to explain what creating a timeline entails, its impact on existing data, or how to use the parameters. The agent would struggle to use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention any parameters or their meanings. The input schema provides field descriptions, but the tool description adds no value beyond what the schema already provides. With 0% schema coverage in the description, the agent gains no additional parameter insight.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('create') and the resource ('timeline') with context ('in Metabase'). However, it does not differentiate from sibling tool create_timeline_event, which is a related but distinct operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., create_timeline_event). No context about prerequisites or exclusions is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description fails to disclose any behavioral traits. It does not mention side effects, required permissions, or what the autocomplete suggestions contain (e.g., tables, fields, or queries).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it lacks structure and is under-specified. It does not earn its place by providing necessary detail, making it inefficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested parameters, no output schema, no annotations), the description is completely inadequate. It does not explain what the tool returns or how to interpret the results, leaving the agent with insufficient information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema parameters have descriptions (e.g., 'Database ID', 'Prefix string'), but the context indicates 0% schema description coverage. The tool description adds no additional meaning beyond the schema, leaving parameters like 'substring' under-explained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and resource ('autocomplete suggestions for a database'), which is specific. However, it does not differentiate from sibling tools like 'get_database_card_autocomplete', which could be confused for a similar function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as 'get_database_card_autocomplete' or search tools. The description lacks exclusions or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the full burden. It only states 'get a map tile' without disclosing behavior such as what the tile represents, expected response format, or side effects. This is insufficient for a tool with 4 parameters and no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks structure. No additional details or headings are provided, making it overly minimal for a tool of this complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input, 4 parameters, no output schema, and many sibling tile tools, the description is severely incomplete. It fails to explain return values, coordinate system, or how to construct the input object correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for the nested parameters (token, zoom, x, y). The description adds no meaning to these parameters, leaving the agent to infer their roles. The token's purpose, coordinate bounds, and zoom levels are unspecified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool gets a map tile for a preview embedded card, specifying the resource and action. However, it does not differentiate from sibling tools like get_embed_card_tile or get_preview_embed_dashboard_tile, leaving ambiguity about its unique scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidelines provided on when to use this tool versus alternatives. The description lacks context for usage scenarios, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only says 'Get', implying a read operation, but does not confirm read-only behavior, discuss side effects, or specify any constraints like authentication needs or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 12 words, which is concise. However, it sacrifices completeness and does not use front-loading effectively to convey key information first.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of nested parameters and many sibling tools, the description is extremely incomplete. It does not explain what a 'cell' is, what the 'automagic dashboard' contains, what the comparison entails, or what the return value looks like.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 5 required sub-properties with zero description coverage. The description does not mention any parameters, leaving the agent to infer from parameter names alone. This fails to add semantic meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it gets a comparison x-ray automagic dashboard for a cell of an entity, which clarifies the tool's purpose. However, terms like 'automagic dashboard' and 'cell' are not defined, and the description does not distinguish from siblings like get_xray_entity_cell or get_xray_entity_compare, leaving ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives such as get_xray_entity_cell or get_xray_entity_compare. The description does not provide context, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description only states 'force a full reindex' without disclosing any behavioral traits such as impact on system performance, required permissions, or side effects like clearing caches or invalidating other data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but at the expense of necessary detail. It fits the tool's purpose but could be more informative without being overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a full reindex operation and the lack of annotations and output schema, the description is severely incomplete. It does not explain what happens during reindexing, the return value, or any implications for the system.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter 'input' of type object with no properties, and the description provides no explanation of this parameter. With 0% schema coverage, the description completely fails to add meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'force a full reindex' and the resource 'search index in Metabase'. It distinguishes from sibling tools like 'search' and 'reinit_search' by specifying 'full reindex', but does not explicitly differentiate from 'reinit_search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance provided on when to use this tool versus alternatives like 'reinit_search', nor any prerequisites or conditions for use. The description lacks context on appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a read-only operation ('Get') but provides no details on side effects, authentication needs, or what happens when invoked. With no annotations, the description fails to disclose behavioral traits beyond the verb.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence but lacks substance. It is under-specified rather than concise, omitting critical details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, no annotations, and a vague description, the tool definition is incomplete. The agent cannot determine what the tool returns or how to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one required parameter 'input' which is an empty object, but the description does not explain its purpose or expected structure. The agent has no guidance on what to pass.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it retrieves 'trash collection' from Metabase, indicating a read operation on trash items. However, it does not specify what the trash collection represents (e.g., list of deleted items) or elaborate on the resource, leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description lacks context on prerequisites or scenarios where retrieving trash collection is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only states the action without indicating side effects, permissions, or whether it is read-only. Agents have no insight into safety or restrictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (7 words) but omits critical details. It is under-specified rather than efficiently concise, lacking context needed for tool selection and invocation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of virtual databases in Metabase and lack of output schema, the description is inadequate. It does not explain the return format, what datasets include, or any edge cases, making it insufficient for correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% according to context, and the tool description adds no meaning to the single parameter 'virtual_db' beyond the schema's minimal 'Virtual database ID'. The description fails to explain how to obtain or use this ID.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'get' and the resource 'datasets for a virtual database', identifying the tool's purpose. However, it does not clarify what constitutes a 'dataset' in Metabase, leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get_database_metadata, get_database_virtual_schema, or other retrieval tools. The description does not mention prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully disclose behavior. It does not explain what an x-ray dashboard is, side effects (likely read-only), required permissions, or that it compares two entities. The term 'automagic' is informal and uninformative.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence is concise but at the expense of clarity. It lacks structure and key details, making it insufficient for proper tool selection.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations put full burden on the description. It fails to explain return value, comparison logic, or differentiate from many sibling get_xray tools. Extremely incomplete for the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the parameters. The schema has 0% coverage (top-level 'input' lacks description) and the description does not compensate by explaining the required entity, comparison_entity, and their IDs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description mentions 'comparison x-ray' and 'dashboard', indicating a comparable dashboard, but fails to clarify that it compares two entities. The phrase 'for an entity' is ambiguous given the tool's name implies a comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over siblings like get_xray_entity or get_xray_entity_cell_compare. The description does not mention prerequisites, context, or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully explain behavior. It indicates an upsert operation but provides no details on side effects, required fields for updates, or authentication needs. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise. However, it is overly minimal and lacks crucial details, so while it is short, it does not earn its place by providing sufficient information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (nested input object, no output schema, low schema coverage), the description is far from complete. It does not explain the dashboard object structure, required vs optional fields, or how errors are handled.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no value beyond the input schema. The schema has 0% description coverage, and the description does not explain what fields the dashboard object should contain, leaving the agent without guidance on constructing the input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it saves a dashboard (creates or updates), which is a specific verb-resource pair. However, it does not distinguish from sibling tools like create_dashboard and update_dashboard, which are more explicit about their actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_dashboard vs update_dashboard). No prerequisites or context are given, leaving the agent to guess the appropriate scenario.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only says 'execute a query', giving no indication of side effects, authorization requirements, or whether the operation is read-only. This is insufficient for agents to reason about safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is too brief to be useful. It lacks necessary detail while being concise, but conciseness without substance is not valuable. The sentence does not earn its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested input object, many sibling tools, no output schema, no annotations), the description is grossly incomplete. It fails to explain how to structure the input, what the output contains, or when to use this vs. similar execute tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention any parameters. Despite a schema with multiple fields (id, dashcard_id, card_id, parameters), there is no explanation of their meaning or interplay. Schema coverage is 0%, and the description adds no value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('execute') and resource ('dashcard query') and mentions 'dashboard filter parameters'. However, it does not differentiate from sibling tools like 'run_dashcard_query' or 'execute_dashcard_action', which perform similar functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidelines are provided about when to use this tool versus alternatives. There is no discussion of prerequisites, recommended inputs, or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. The single sentence only restates the tool's purpose without mentioning effects such as whether it is read-only (export typically is, but not guaranteed), whether permissions are needed, or what happens when the dashcard has no query. This is insufficient for the agent to understand behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it is under-specified. It lacks structure, such as noting required parameters, return type, or usage examples. Every sentence should provide necessary information; here, the single sentence fails to convey enough detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With a nested input schema and no output schema, the description must compensate by explaining what the export produces (e.g., file download, URL, stream), how format options work, and error conditions. It provides none of this, leaving the tool highly incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema contains 6 parameters (including nested) with basic descriptions like 'The card ID' and 'Parameter values'. Schema description coverage is marked as 0%, meaning these are not considered descriptive. The description adds no additional meaning or context for any parameter, such as format constraints, dependencies, or default behavior. This provides no added value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Export query results for a dashcard in Metabase' clearly states the verb 'Export' and the resource 'query results for a dashcard'. This differentiates it from sibling tools like export_card_query (exports query results for a card) and export_dashboard_card_query (likely similar but naming suggests a different target). However, it does not explicitly contrast with siblings, so the purpose is clear but not fully distinguished from very similar named tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as export_card_query or export_dashboard_card_query. There is no mention of prerequisites, context, or exclusions. This leaves ambiguity for the agent in selecting the correct tool among similar ones.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior, but it only states the action. It does not reveal whether the token is persisted, returned, or what side effects occur. The agent is left uninformed about the token's lifecycle or storage implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but at the expense of essential information. It omits critical details about the token's nature, return value, and parameter usage. True conciseness balances brevity with completeness, which is not achieved here.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations, output schema, and rich context from sibling tools, the description is severely incomplete. It does not explain the token's purpose, behavior, or response format, making it insufficient for an AI agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a single required parameter 'input' (an empty object) with 0% schema description coverage. The description adds no meaning about this parameter, leaving its purpose entirely unspecified. The agent cannot determine what to provide for 'input' or if it is truly required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: generate a random token in Metabase. It uses a specific verb and resource, making the core purpose understandable. However, it does not differentiate from sibling tools that also generate tokens (e.g., create_api_key, regenerate_api_key), lacking specificity about the token's domain or use case.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description fails to mention prerequisites, context, or exclusions (e.g., whether this is for temporary tokens, authentication, or other purposes). Without this, an AI agent cannot effectively decide when to invoke this tool over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It does not mention that this is a read-only operation, what the response format is, or any prerequisites. The description adds minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is overly terse (one short sentence) and omits critical details. Conciseness is beneficial only when the description is still informative, which it is not here.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of nested parameters, lack of output schema, and numerous sibling tools, the description is far from complete. It does not explain return values, parameter semantics, or usage scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and the description adds no parameter information. It does not explain the 'parameter' object or the 'field_ids' array, leaving the agent without clues about how to construct valid inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'values for a dataset parameter' within the context of Metabase. However, it does not differentiate from sibling tools like get_card_param_values or get_dashboard_param_values, which also get parameter values but for different scopes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. Given many sibling tools for similar purposes, explicit usage context is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It does not mention authentication requirements (token), return type (likely an image), or any side effects. For a tool that accesses embedded resources, this is a significant omission.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but under-specified. It lacks structure such as separating purpose from details, and the brevity sacrifices clarity. Every word earns its place, but more content is needed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (6 required parameters, many siblings, no output schema, no annotations), the description is critically incomplete. It provides only the barest hint of functionality, leaving the agent unable to invoke the tool correctly without external knowledge.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the description does not explain the parameters at all. The input object has required fields (token, zoom, x, y, card_id, dashcard_id) but none are described. The tool name and description imply coordinates and zoom, but explicit semantics are missing, making invocation error-prone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get) and resource (map tile for an embedded dashboard dashcard), using specific terms like 'map tile' which narrows the scope. However, it does not differentiate from sibling tools like get_embed_card_tile or get_public_dashboard_tile, which have similar purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. Sibling tools include many tile-retrieval functions, but the description lacks any context for selection or exclusions, leaving the agent without decision criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only states the tool gets oEmbed metadata but does not disclose any behavioral traits, such as whether it is read-only, any required permissions, or the structure of the response.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, but it is too terse. Critical details about parameters and usage are missing, making it under-specified rather than appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and the need to understand oEmbed protocol, the description is severely incomplete. It does not explain what oEmbed metadata is, what the response format looks like, or how parameters affect the result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain any parameters. The nested 'input' object with 'url', 'maxwidth', 'maxheight' is entirely undocumented, leaving the agent with no guidance on how to use these fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets oEmbed metadata for a public Metabase resource. However, it does not differentiate this from other public resource getters (e.g., get_public_card) that might return different formats.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_public_card or get_public_dashboard. The description lacks context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden. It states 'Get' implying a read-only operation, but it does not disclose any behavioral traits such as authentication requirements, rate limits, or side effects. The minimal description leaves agents uncertain about the tool's safety and prerequisites.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (6 words) and lacks structure. While conciseness is valued, this is under-specified; it does not front-load any critical information beyond a basic verb and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's purpose (retrieving form input options) and the absence of an output schema, the description should explain what the returned options look like. It also fails to clarify the input parameter's purpose. The description is incomplete for a tool that likely requires specific input context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, and the description adds no meaning to the lone 'input' parameter. It does not specify what properties or format the input object should have, leaving the agent with no usable guidance beyond the schema's empty definition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Get') and the resource ('form input options for creating a pulse'). It distinguishes from sibling tools like 'get_pulse' (which retrieves existing pulses) and 'create_pulse' (which creates a pulse). However, 'form input options' is vague and could be more precise about what exactly is returned.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. For example, it does not mention that this tool should be called before 'create_pulse' to retrieve required fields, nor does it exclude other contexts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It states 'list all virtual tables' but the parameter restricts to one database, which is not mentioned. Side effects, read-only nature, and return format are absent, and the scope inaccuracy undermines transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence and concise, but the inaccuracy (scope mismatch) detracts from structural quality. It is not optimally front-loaded with the most critical constraint (the required virtual_db).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not mention the required virtual_db input, return format, pagination, or what constitutes a virtual table. Given no output schema, the description should cover these aspects but fails to do so, leaving significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a description for the 'virtual_db' parameter ('The virtual database ID to list datasets for'). The tool description adds no additional meaning. Schema description coverage is effectively 100% (as seen in the provided schema), so baseline is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it lists virtual tables (saved questions), but inaccurately claims it does so 'across all databases', contradicting the required parameter 'virtual_db' which filters by a single database. The verb and resource are clear, but the scope is misleading, reducing clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus siblings like 'list_database_virtual_tables' or 'list_all_tables'. The description lacks context for selection, leaving the agent to infer usage from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It does not disclose that rescanning is a write operation, its side effects (e.g., cache update, sync trigger), or any required permissions. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, but it under-specifies the tool's behavior. It is not appropriately sized for a tool with no annotations and zero schema coverage, missing key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and low schema coverage, the description is severely incomplete. It does not explain the effect, prerequisites, response, or relation to sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema coverage is 0%, and the description adds no meaning beyond the schema's 'Database ID' label. The sole parameter 'input' with nested 'id' is not elaborated. Essential parameter context is missing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Rescan field values) and the target (a database in Metabase). It is specific enough to distinguish from the sibling tool 'rescan_field_values', which targets a field, but does not explicitly differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'rescan_field_values' or 'discard_database_values'. The description lacks context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits (e.g., whether the sync is destructive, if it triggers a database update, or if it affects existing data). The agent has no information about side effects or safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it concise. However, it is too minimal and misses important details. While it serves a basic purpose, it could be more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter) but lacking annotations and output schema, the description is incomplete. It does not explain the sync operation's scope, effects, or expected outcomes, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage (only 'Table ID' is stated in the schema). The description does not explain the parameter 'id' or provide any additional context. It adds no value beyond the schema's minimal hint.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Sync') and the resource ('the schema for a table in Metabase'). It is specific to a table, not a database. However, it does not differentiate from similar sibling tools like 'sync_database_schema' or 'resync_table_fields', which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or exclusions. The description fails to help the agent decide among similar sync tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a mutation (reordering) but lacks details on side effects, required permissions, or whether changes are reversible. With no annotations provided, the description fails to disclose behavioral traits beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one sentence) but lacks detail to be useful. It is front-loaded, but underspecification reduces its value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, no output schema, and the complexity of having a nested input object, the description is severely incomplete. It does not cover return values, error handling, prerequisites, or any additional context needed for safe invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add any meaning beyond the input schema. Although the schema itself includes property descriptions, the tool description makes no mention of parameters, and schema coverage is 0%, so it fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Reorder fields in a table' and specifies the product 'Metabase'. It distinguishes from sibling tools like 'update_table' or 'update_field' by focusing specifically on field order reordering.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'update_table' or 'update_field'. There is no context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral traits beyond 'copy'. No annotations are present, so the description should explain if the original card remains unchanged, authentication requirements, or side effects. This is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but overly brief for a tool with multiple parameters. It lacks structure to efficiently convey necessary information, though it is not verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested object, three parameters, no output schema or annotations), the description is severely incomplete. It does not explain what happens to the original card, the return value, or any constraints like permissions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description adds no meaning beyond the schema. It does not explain the purpose of 'name' or 'collection_id', leaving the agent to infer from parameter names alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Copy') and the resource ('an existing card (saved question)'). It distinguishes from siblings like 'create_card' and 'copy_dashboard' by specifying the operation and resource type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., 'create_card' or 'bulk_move_cards'). There is no mention of prerequisites, typical use cases, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states the creation action but omits any side effects (e.g., whether it's idempotent), authentication requirements, rate limits, or what happens on success/failure. The agent lacks critical behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one sentence, 6 words). While conciseness is generally positive, here it comes at the expense of completeness. It earns its place by stating the core action but does not provide enough detail for effective tool selection and invocation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of this tool (nested input parameter, no output schema, no annotations, and multiple sibling creation tools), the description is insufficient. It fails to explain what a notification channel is, valid types, required details configuration, or expected outcomes. The agent would likely need to guess or consult external documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the description adds no information about parameters. The description does not mention the 'input' object or its properties (name, type, details, active, description). With low coverage and no parameter info in the description, the agent must rely solely on the schema, which lacks enum values for 'type' and detailed context for 'details'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and resource ('new notification channel'), and the context of usage ('in Metabase'). It effectively differentiates from sibling tools like update_channel, get_channel, list_channels, as it focuses solely on creation. However, it does not elaborate on what constitutes a notification channel, which could be inferred but is not explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., update_channel, test_channel), nor does it mention prerequisites, permissions, or typical use cases. The agent receives no contextual hints about appropriate scenarios for channel creation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only says 'Delete' without disclosing consequences, such as whether the deletion is irreversible, if it affects active keys, or what happens to associated data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence of 6 words is concise but lacks structure. It is not front-loaded with key information and could be expanded without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter destructive operation, the description is minimal. It lacks details like id format, confirmation, or output. No annotations or output schema exist to supplement.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Description does not mention the 'id' parameter. With 0% schema description coverage, the description must compensate but adds no value beyond the schema. The schema has a basic description for 'id' but that is not sufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'delete' and resource 'API key', with scope 'from Metabase'. It distinguishes from other delete tools by specifying the resource. However, it could be more precise about permanence or effect.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'update_api_key' or 'regenerate_api_key'. No context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavioral traits. It does not mention side effects, idempotency, authentication requirements, or possible errors. The description only states the action, not the behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded, but it sacrifices informativeness for brevity. It could be slightly longer without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and many sibling tools, the description is incomplete. It does not explain return values, error handling, or prerequisites, making it hard for an AI agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description does not add any new semantics beyond what is already in the schema (e.g., 'Action ID to execute'). It fails to clarify parameter constraints, formats, or dependencies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it executes an action with parameters, which conveys the basic purpose. However, it is vague about what 'action' refers to (e.g., custom action, database action) and does not distinguish it from sibling tools like execute_card, execute_query, or execute_dashcard_action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives. Given many execute-related siblings, the description should specify scenarios or prerequisites, but it does not.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description states only 'Execute a public action,' lacking disclosure of behavioral traits such as authentication needs, side effects, error states, or success conditions. Agent cannot infer safety or implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but lacks structure. Could be expanded with brief context about public actions or parameter construction without adding bulk.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations, and a one-line description. Agent lacks information about return values, how to obtain a public UUID, whether the action writes data, or error handling. Incomplete for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema provides descriptions for 'uuid' and 'parameters', so tool description does not need to repeat. Baseline of 3 is appropriate given schema covers parameter meaning, though schema_description_coverage is listed as 0% (likely error).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'Execute a public action in Metabase,' clearly identifying verb and resource. However, it does not distinguish from sibling 'execute_public_dashcard_action' or explain difference from 'execute_action'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'execute_action' or 'execute_public_dashcard_action'. Missing prerequisites, public access requirements, or common scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for behavioral disclosure. It only states the basic action without mentioning authentication requirements, side effects, return type (e.g., file), error behavior, or idempotency, which is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise at one sentence, but it lacks structure (e.g., separating purpose, parameters, behavior). It omits necessary details, making it under-specified for the tool's complexity (nested input, multiple required fields).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested parameters) and the absence of an output schema, the description should explain return value (e.g., file download) and context among similar siblings. It only covers a fraction of needed information, leaving the agent ill-equipped.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema (with 0% description coverage) already describes parameters, but the tool description adds no semantic value beyond redundantly listing export formats. It fails to explain how the nested input object works or the relationship between parameters, offering minimal aid to an agent.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool exports a dashcard query result in specific formats (csv, json, xlsx, pdf). However, it fails to distinguish from the sibling tool 'export_dashcard_query', which shares an almost identical name and purpose, leading to potential confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'export_card_query' or 'export_dashcard_query'. It does not mention context, prerequisites, or exclusions, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It only states 'Export results' without clarifying side effects (read-only), authentication needs, or return format behavior. Missing details on whether the tool downloads a file or returns data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One very short sentence, but it omits essential details. For a tool with a complex input schema, this is under-specified rather than concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so description should describe the return value (e.g., file download). It does not. The description lacks completeness for an agent to correctly invoke the tool, especially given the nested parameter structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% for the 'input' object; only 'export_format' has a minimal description ('Export format'). The description adds no explanation of the token required or the meaning of export_format values. With nested parameters, this is insufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Export results of an embedded card query') and the platform (Metabase). It distinguishes from siblings by specifying 'embedded card query', but does not explicitly differentiate from similar tools like export_embed_dashcard_query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., export_card_query, export_embed_dashcard_query). No context provided about prerequisites or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavior like whether this triggers a download, returns data directly, or requires specific permissions. It only says 'Export results' without any details on side effects or authorization needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no redundancy. However, it is too brief for a tool with a complex input schema and many siblings. Could benefit from additional context without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested parameter, multiple sibling export tools, no output schema), the description is insufficient. It does not clarify the relationship to other exports, the public nature of the card, or what the output contains.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage for the nested 'input' parameter. The description does not explain what 'uuid' represents (likely the public card's UUID) or the significance of 'export_format' (csv/json/xlsx). No additional meaning is provided beyond the schema structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it exports results of a public card query in Metabase. The verb 'Export' and resource 'public card query' are specific. However, it does not distinguish between this and similar tools like export_card_query, but the name itself conveys the public aspect.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as export_card_query or export_public_dashcard_query. Does not mention prerequisites (e.g., the card must be public) or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden for behavioral transparency. It does not state whether this is a read-only operation, what the return format is (file download?), or any side effects. The description is too sparse to inform the agent about behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence) but at the expense of completeness. It front-loads the purpose but fails to earn its place by omitting critical details. A middle ground between conciseness and informativeness is missing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters nested in an object, no output schema, and no annotations, the description is insufficient. It doesn't explain how to obtain required identifiers (e.g., uuid) or what the export format options imply. The agent is left guessing about prerequisites and results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. The schema has 0% description coverage (except export_format's brief 'Export format'), and the description does not explain what uuid, dashcard_id, or card_id represent. The agent gets no semantic help beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Export results of a public dashcard query in Metabase' clearly identifies the action (Export) and the resource (results of a public dashcard query). It distinguishes from siblings like export_card_query by specifying 'public' and 'dashcard', though it could be more explicit about what makes a dashcard 'public'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives like export_public_card_query or export_dashcard_query. No prerequisites or context about public vs. private dashcards are mentioned, leaving the agent without decision-support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It only states the operation is a 'get' (read), but fails to disclose any behavioral traits such as error conditions, rate limits, or response format. The description is too minimal for safe autonomous invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it sacrifices informativeness for brevity. It front-loads the core purpose but does not earn its place by adding value beyond the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description should provide more context about return values, potential errors, and how this tool relates to sibling tools like get_card_param_remapping or search_card_param_values. It is incomplete for effective tool selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the tool description adds no parameter semantics beyond the schema's property descriptions ('Card ID', 'Parameter key (slug)'). The description does not elaborate on the meaning or usage of the `id` and `param_key` parameters, leaving the agent to rely solely on the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves possible values for a card filter parameter, using specific nouns ('card', 'filter parameter') and a verb ('get'). It distinguishes from related tools like get_card_param_remapping, but does not explicitly differentiate from search_card_param_values, so it gets a 4.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like search_card_param_values or get_card_param_remapping. There are no prerequisites, exclusions, or context for effective use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits, but it only states the action without any context such as error handling, authentication requirements, or what 'related items' entails. It lacks transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but at the expense of clarity. It could be more informative without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is insufficient. It does not explain the return type or structure of 'related items', leaving the agent guessing about the response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, meaning the description should compensate for parameters. Parameter 'id' is described only as 'The dashboard ID' in the schema, and the description adds no further meaning or constraints (e.g., format, range, required permissions).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Get related items for a dashboard', which is a specific verb-resource pair but 'related items' is vague. It does not specify what kind of items (e.g., cards, metrics, segments) are returned, leaving ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternative like get_dashboard_items, get_dashboard_metadata, or other 'get_dashboard_*' siblings. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description fails to disclose any behavioral traits such as required permissions, data freshness, or whether the operation is read-only. The minimal statement 'Get usage information' does not compensate for the lack of annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only one sentence, which is too sparse. It is under-specified rather than concise, failing to provide necessary context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is extremely incomplete. It does not define 'usage information', lacks output schema, fails to mention prerequisites or return format, and does not compensate for the lack of annotations and output details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain the parameter. Although the schema provides 'Database ID' for the 'id' parameter, the tool description adds no value beyond the schema for a tool with poor coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb-get-and resource-database, and includes 'usage information' which distinguishes it from siblings like get_database, get_database_metadata, and get_database_healthcheck. However, it does not explicitly differentiate itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the many similar database-related get tools. The description provides no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description bears full responsibility for behavioral disclosure. It states the tool 'gets' a document, implying a read-only operation, but it does not explicitly confirm idempotency, lack of side effects, or any required permissions. For a simple read, this is minimal but acceptable; higher scores would require explicit safety statements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is succinct with one sentence, but it lacks essential detail. Conciseness should not come at the cost of completeness; this is under-specified rather than appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should clarify what a 'document' is in Metabase, provide expected return values, or relate to other document tools. It does none of these, leaving significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter 'id' with a description 'Document ID' in the schema, but the context indicates 0% schema description coverage, meaning the tool description fails to add any meaning beyond the raw schema. The description does not explain what constitutes a document or how to obtain the ID.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get a document by ID in Metabase' clearly states the verb and resource, making the purpose obvious. However, it does not differentiate from sibling tools like get_public_document or get_public_document_card, which also retrieve documents but with different scopes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool over alternatives, nor any prerequisites or context. The description does not mention any conditions or exclusions, leaving the agent to guess.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It only says 'get a map tile' without noting that it is read-only, what the output format is (likely an image), validation constraints on parameters, or error conditions. The required 'token' parameter is unexplained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it lacks structure (e.g., bullet points, usage hints). It is under-informative for a tool with multiple required, non-obvious parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (four parameters with geographic semantics), no output schema, and no annotations, the description is incomplete. It does not explain map tile conventions, coordinate system, expected return type, or error handling. The agent is left with significant ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and the description adds no explanation for any of the four parameters (token, zoom, x, y). The agent must infer meaning solely from names, which is insufficient for correct invocation (e.g., tile coordinate system, zoom range, token source).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the specific resource ('map tile for an embedded card') and action ('get'), but does not differentiate from siblings like get_preview_embed_card_tile or get_card_tile. It is clear on its own but lacks distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., get_card_tile, get_public_card_tile). There are no prerequisites, context descriptions, or exclusions. The agent receives no situational advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavior. It only says 'compute breakout values' without explaining what that entails, whether it requires an existing metric, or what the output format/likely is.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single short sentence with no unnecessary words. It's appropriately concise, though it sacrifices completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given one parameter with 0% schema coverage, no output schema, and no annotations, the description is severely incomplete. It fails to explain what the tool returns or any important usage constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%: the sole parameter 'definition' is an object with no property descriptions. The description adds 'MBQL metric definition' as a hint, but this is insufficient for a complex nested object. The agent lacks guidance on how to construct the MBQL definition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('compute') and resource ('breakout values for a metric definition'), distinguishing it from siblings like get_metric (which returns metric metadata) and get_metric_dataset (which returns a dataset). It could be more explicit about how it differs from search_metric_dimension_values or get_metric_dimension_remapping.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_metric_dimension_values or search_metric_dimension_values. No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral traits beyond the basic action. It does not state whether the operation is read-only, what happens if the remapping is not found, or any required permissions. Since no annotations are provided, the description carries this burden but fails to deliver.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks important detail. It is front-loaded with the action, but the brevity results in missing contextual information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, annotations, and the presence of nested objects, the description is insufficient. It does not explain what the remapping looks like or how the output is structured, leaving the agent with incomplete information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0% for the top-level input parameter, and the tool description adds no parameter information beyond what is already in the nested schema. The description does not explain how the parameters relate to each other or provide usage examples.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly uses the verb 'Fetch' and specifies the resource 'remapping for a dimension value of a metric in Metabase'. However, it does not differentiate from sibling tools like get_metric_dimension_values or get_metric, which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., get_metric_dimension_values, get_card_param_remapping). There are no prerequisites or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry the burden. It only states the basic action without disclosing behaviors such as authentication requirements (public implies none), what happens if the card is not a map, or any rate limits. Minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no fluff, but it is underspecified. It could include more context without becoming verbose. Adequate but minimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 parameters, nested object, no output schema, no annotations) and many siblings, the description is extremely incomplete. It lacks parameter explanations, return value description, and differentiation from similar tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%; the description provides no explanation for parameters (uuid, zoom, x, y). The description fails to add meaning beyond the schema, e.g., what uuid refers to, zoom level range, or coordinate meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly indicates this tool retrieves a map tile for a public card in Metabase, using a specific verb and resource. However, it does not differentiate from siblings like get_card_tile or get_card_map_tile.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs. alternatives (e.g., get_card_tile for private cards, get_public_card for full card data). No exclusions or contexts provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits such as authentication requirements, cost, or return value. It only implies a read operation via 'Get', but fails to mention that the output is likely a JSON object of weights or that the operation is safe.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 7 words, which is concise but lacks structure. It conveys the basic purpose but omits important details that could fit without increasing length significantly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (get operation with no effective parameters and no output schema), the description is incomplete. It does not explain what the weights represent, how they are used, or what the response format is, leaving the agent with insufficient information for reliable invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one required parameter 'input' which is an empty object with no properties. Schema description coverage is 0%. The description adds no meaning to this parameter, leaving the agent unsure why it is required or what to provide. It could have been omitted entirely.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('search result ranking weights'), and the tool name 'get_search_weights' matches. The presence of a sibling 'update_search_weights' helps distinguish this as a read operation, but the description itself does not further differentiate from other get tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'reinit_search' or 'force_reindex_search'. There is no mention of prerequisites or exclusions, leaving the agent without context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only implies a read operation but omits details on pagination, limits, authentication, or side effects. The agent gains minimal insight beyond the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence), but it is overly minimal. While it wastes no words, it sacrifices informativeness for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (one parameter, no output schema, no annotations), the description is insufficient. It does not explain what 'data rows' entails or provide enough contextual details for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no meaning to the 'id' parameter. The description fails to compensate for the lack of parameter documentation, leaving the agent to infer that 'id' is a table ID.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get data rows') and resource ('from a table in Metabase'). It is specific and distinguishable from sibling tools like 'get_table' or 'get_table_metadata', though it does not explicitly differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description does not mention any context, prerequisites, or exclusions, leaving the agent to infer usage from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states the function. It does not disclose behavioral traits like read-only nature, required permissions, side effects, or pagination. The 'get' prefix implies read-only, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 8 words, which is concise but lacks substantive information. While brevity can be good, here it sacrifices clarity and completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (1 param with empty nested object, no output schema), the description is insufficient. It does not explain the return value, the purpose of the input object, or how the tool fits into the broader task run context. More detail is needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, and the description adds no meaning about the single required parameter 'input' (an empty object). The description does not hint at what the input should contain (e.g., task run ID), leaving the parameter semantics entirely undefined.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get entity types tracked by task runs in Metabase' specifies the verb (Get) and the resource (entity types tracked by task runs), clearly distinguishing from siblings like get_task_run or list_task_runs. However, it does not clarify what constitutes an 'entity type', leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as when to use get_task_run or list_task_runs. It does not mention any prerequisites or typical scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states 'Get' without confirming read-only behavior, side effects, authorization needs, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, but it uses jargon ('automagic dashboard') that may be unclear. It is short but not effectively informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the high complexity (nested input, many siblings, no output schema), the description is severely lacking. It fails to explain the comparison, rule application, output format, or how it differs from other X-ray tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain any of the six required parameters (entity, prefix, dashboard_template, etc.). The parameter names are ambiguous without elaboration.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly indicates it gets a comparison x-ray dashboard for an entity with a rule, but does not differentiate from similar siblings like get_xray_entity_compare or get_xray_entity_cell_rule_compare.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the many other X-ray tools. No examples or prerequisites are given, leaving the agent without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility for behavioral disclosure. It only states the action without revealing any behavioral traits such as authorization requirements, side effects, or whether the operation is reversible. This is insufficient for an AI agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it brief. However, it is too sparse given the complexity of the input schema. It sacrifices necessary detail for brevity, earning a middle score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without annotations, output schema, or parameter descriptions, the tool description is severely incomplete. It fails to cover return values, the meaning of model/model_id, or the tool's effect on the system, leaving major gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a nested object with two parameters (model and model_id) and 0% description coverage. The tool description does not explain these parameters at all, leaving the agent without guidance on how to populate them correctly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Invalidate cached query results in Metabase' clearly states the action (invalidate) and the resource (cached query results in Metabase). It is specific but does not differentiate from siblings like 'delete_cache_config' or 'refresh_persisted_model', which might have overlapping functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives, nor does it mention prerequisites, exclusions, or context-specific applicability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description does not disclose any behavioral traits (e.g., read-only, no side effects, pagination, authentication requirements). For a list tool, expected to be read-only but not stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but too minimal; lacks structure or any additional context. Could be more informative without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite being a simple list tool, the description fails to mention what the output contains (e.g., measure IDs, names), pagination, or any results structure. Incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has one required parameter 'input' with no properties and no description. The description adds no meaning beyond the schema; 0% schema description coverage. The input object's purpose is unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'List' and resource 'all measures in Metabase'. While it distinguishes from siblings like 'list_metrics' and 'list_segments', it does not explain what a measure is, but the name suffices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like 'list_metrics' or 'list_segments'. No context about prerequisites or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It lacks detail on side effects, required permissions, or what enabling persistence entails (e.g., creating a table). The description is too brief to disclose behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at one sentence, but it lacks structure and omits important information. It is minimally acceptable but not well-organized for agent comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description should provide more context about the effect and outcome of enabling persistence. It is incomplete for an agent to understand the tool's full behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not mention any parameters; the sole parameter 'card_id' is only documented in the input schema. With 0% schema coverage in the description, it adds no meaning beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Enable model persistence for a card/model in Metabase,' which gives a clear verb and resource. However, it does not differentiate from siblings like 'enable_model_persistence' or clarify what 'model persistence' specifically means in Metabase.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., 'enable_model_persistence' or 'unpersist_card'). No prerequisites or context are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the full burden. It only discloses the 'admin only' constraint but omits other behavioral traits such as what the preview returns (e.g., dashboard view, data), whether it requires authentication beyond admin status, or if it has any side effects. The description is insufficient for an agent to understand the tool's full behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise and front-loaded with the key verb. However, it may be too short, sacrificing necessary detail. Every word earns its place, but the brevity hinders completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and the complexity of an embedded dashboard preview, the description does not explain what the tool returns or the nature of 'preview'. It does not address how it differs from similar tools like 'get_embed_dashboard' or what the output format is. The description is incomplete for an agent to reliably use this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no detail about the 'token' parameter beyond mentioning 'by token'. It does not explain what the token represents, how to obtain it, or any format requirements. The nested object structure is not clarified, leaving the agent without meaningful guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies 'Preview an embedded dashboard by token from Metabase (admin only)', which clearly indicates the verb (preview), resource (embedded dashboard), and the method (by token). The 'admin only' constraint adds clarity. It distinguishes from siblings like 'get_embed_dashboard' and 'preview_embed_card', though could be more explicit about the difference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The only hint is 'admin only', which is a prerequisite but not a usage context. There is no mention of when not to use it or which sibling to prefer for similar tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as idempotency, side effects, or rate limits. It implies a read operation but does not explicitly state safety considerations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence). While concise, it sacrifices needed detail. The structure is acceptable but not optimized for quick comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema and lack of output schema or annotations, the description is insufficient. It does not explain the preview behavior, output format, or how it relates to similar tools in the sibling list.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (the parameters token and param_key are not described in the description). The description adds no meaning beyond the schema, failing to explain what these parameters represent or how they should be used.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Preview' and the resource 'parameter in an embedded dashboard from Metabase (admin only)'. However, it does not differentiate from siblings like 'get_embed_dashboard_params' or 'search_embed_dashboard_params', which may have similar purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. No exclusions or context are provided, leaving the agent to infer usage from the name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description lacks details on behavioral traits such as destructive effects, required permissions, or side effects. Without annotations, the agent has no insight into risks or outcomes beyond the vague 're-initialize'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words, but it is too brief to be helpful. Conciseness is not achieved at the expense of completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, minimal documentation of parameters, and absent output schema, the description is severely incomplete. The agent cannot determine what input is required, what the operation entails, or what to expect as a result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'input' is an object with no defined properties, and the description provides no explanation of its structure or purpose. With 0% schema coverage, the description fails to add any semantic value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reinitializes the search index in Metabase. However, it does not differentiate from the sibling tool 'force_reindex_search', which likely has a similar purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'force_reindex_search'. There is no mention of prerequisites, use cases, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It does not mention any behavioral traits such as authentication requirements, whether the query is read-only, potential costs, or side effects. For an execution tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise. However, conciseness is not helpful if it omits critical information; the sentence barely adds value beyond the name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (executing a query, nested input, no output schema), the description is severely incomplete. It fails to explain what an embedded card is, how to obtain the token, what the response looks like, or any constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate for the undocumented parameter. However, it does not mention the 'token' parameter at all, leaving its purpose and format entirely unknown.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the verb 'Run' and resource 'pivot query for an embedded card', so it is clear about the basic action. However, it does not distinguish from siblings like 'run_embed_dashcard_query' or 'execute_card_pivot', which means the agent might not know which tool to pick.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The sibling list contains many similar query execution tools, but the description offers no context or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits like read-only vs destructive, permissions, or side effects. 'Run a query' implies execution but does not clarify if it mutates data, requires specific authentication, or has rate limits. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but too brief. It front-loads the action but does not provide enough substance to justify its length. It could include a brief explanation of parameters or output.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and sparse parameter documentation, the description fails to provide a complete picture. It should mention the return format (query results), error scenarios, and how to obtain a valid token.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the description adds no meaning to the parameters. The three fields (token, card_id, dashcard_id) are unexplained. For a nested object parameter, the description should at least clarify the role of each field.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Run a query') and the resource ('embedded dashcard in Metabase'), which helps differentiate from similar tools like run_dashcard_query (non-embedded) and run_embed_card_query (single card, not dashcard). However, it does not explicitly mention the token-based authentication context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., run_dashcard_query for non-embedded, run_embed_card_query for single cards). The description lacks context about prerequisites or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only says “run a pivot query” without disclosing side effects, authentication needs, rate limits, or whether it is read-only. The behavioral impact is unclear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single 12-word sentence, which is efficient but omits critical details. It earns a 3 because it’s not verbose, but it sacrifices clarity for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a nested object parameter, no output schema, and many siblings. The description fails to explain what a “preview embedded card” is, what the token represents, or what the query returns. It is insufficient for proper usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter (input with a token), but schema coverage is 0% and the description does not explain the token’s purpose, format, or constraints. The description adds no value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states “Run a pivot query for a preview embedded card in Metabase,” which has a specific verb and resource. However, it does not differentiate from siblings like run_embed_card_pivot_query or run_preview_embed_dashboard_pivot_dashcard_query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Among many similar sibling tools, there is no mention of context, prerequisites, or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only says 'Run a query', with no information on side effects, authentication needs, rate limits, or what the query execution entails. This leaves significant ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with one sentence, but it sacrifices necessary detail. It is appropriately short but incomplete.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested object with three required parameters, no output schema), the description is severely lacking. It does not cover what the query returns, any prerequisites, or how to interpret the parameters, making it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema coverage is 0% and the description does not add any meaning to the parameters (token, card_id, dashcard_id). It fails to explain what these parameters represent or how they relate to a 'preview embedded dashcard'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Run a query') and the resource ('preview embedded dashcard'), making the purpose understandable. However, it does not differentiate from sibling tools like run_embed_dashcard_query or run_dashcard_query, as 'preview embedded' is not explained.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. There is no indication of when to use this tool versus alternatives, nor any prerequisites or context for its use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only says 'Run a pivot query' but doesn't clarify if it is read-only, modifies state, requires authentication, or has any side effects. The agent cannot infer safety or preconditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at one sentence but lacks structure. It is front-loaded with the purpose, but misses crucial details. Every word is necessary but insufficient for usability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, no output schema, a complex nested parameter, and no parameter documentation, the description is severely incomplete. The agent cannot effectively use this tool without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description offers no parameter information. The input schema has nested objects (uuid, parameters), but 0% schema description coverage means the schema itself lacks documentation. The description fails to compensate, leaving the agent without guidance on what 'uuid' and 'parameters' mean or how to use them.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it runs a pivot query for a public card, specifying the resource and action. However, it doesn't elaborate on what a pivot query entails, which may be ambiguous for some agents. It distinguishes from siblings like run_dashcard_query by mentioning 'public card'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., run_embed_card_pivot_query, run_dashcard_query). No preconditions or when-not-to-use context is given, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It says 'Search values' implying read-only query, but doesn't disclose rate limits, error handling, or output format. Minimal behavioral info.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence, no fluff. However, the brevity is harmful given the lack of parameter descriptions and missing usage guidance. It sacrifices clarity for conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, no annotations, and 0% schema coverage, the description is insufficient. An AI agent lacks critical information about how to invoke it correctly, especially given many similar sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and description adds no parameter details. The three fields (token, param_key, query) are unexplained. An AI agent must guess their meaning, leading to high risk of misuse.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it searches values for a parameter of an embedded dashboard, which is specific. It distinguishes from siblings like search_dashboard_param_values or search_card_param_values by specifying 'embedded dashboard', but 'search' could be clearer (e.g., filtering vs autocomplete).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like search_embed_card_param_values or get_embed_dashboard_param_values. No prerequisites or context like needing an embedding token.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It fails to disclose behavioral traits: whether the operation is read-only, if authentication is required, or what happens on error. The brief description offers no insight into side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, consisting of a single sentence. While this is efficient, it lacks necessary detail to be useful. The structure is front-loaded with the verb, but the content is insufficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a nested input object, no output schema, and no annotations, the description is severely incomplete. It does not explain the return value, usage pattern, or any constraints, making it inadequate for an AI agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no information about the input parameters (token, param_key, query). The agent cannot infer what each parameter represents or how to use them, leaving a critical gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies the verb 'Search' and the resource 'values for a parameter of a preview embedded dashboard'. It clearly identifies the tool's action and target, but does not differentiate it from similar sibling tools like search_embed_dashboard_param_values or get_preview_embed_dashboard_param_values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not indicate when to use this tool versus alternatives, such as fetching all parameter values or searching in a different embedding context. There is no mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so description carries full burden. It discloses that the pulse is sent immediately (actual execution), but does not reveal whether it is idempotent, what side effects occur (users receive notifications), or whether the action is reversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, but too sparse. Could include more context without significant bloat.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Missing output schema, no explanation of return values or success/failure indicators. For a testing tool with a complex nested parameter, the description is grossly incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (no parameter descriptions). The description adds no meaning about the 'input' or nested 'pulse' object, which is completely undocumented. The agent receives no guidance on how to structure the pulse parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Test a pulse') and the immediate effect ('sending it immediately'). It distinguishes from sibling tools like create_pulse and get_pulse. However, the phrase 'sending it immediately' could be more precise (e.g., triggers the pulse to execute and send notifications).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., test_channel, get_pulse, create_pulse). Does not mention that it is for validation before scheduling, or warn about actual side effects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only states the action without disclosing behavioral traits like side effects, required permissions, or error states. Does not add value beyond stating the purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, clear and front-loaded. However, it is too brief and could include more structured information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of sibling tools and no output schema or annotations, the description is insufficient. It does not explain the expected outcome of the undo action or any constraints, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%. The description does not explain the meaning or purpose of the parameters (hash, email, pulse_id). The input schema provides minimal descriptions, but the description adds nothing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it undoes an email unsubscribe from a pulse. It specifies the action (undo), resource (pulse unsubscribe), and context (email, Metabase). Differentiates from siblings like unsubscribe_pulse and undo_notification_unsubscribe by its specific action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like undo_notification_unsubscribe or unsubscribe_pulse. No context on prerequisites or typical scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states 'update an existing card' without mentioning any side effects, permissions required, or consequences such as whether updates are reversible or affect related entities.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but could be slightly expanded to include more context without becoming verbose. Every word earns its place, but the lack of detail reduces its informativeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested input schema, multiple optional properties, no output schema), the description is minimal. It does not explain the return value, error cases, or the effect of updating various fields. For a tool with many parameters and no annotations, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes full property descriptions, but per the context signal 'Schema description coverage: 0%', the tool description adds no additional meaning to the parameters. With a nested object and multiple optional fields, the description should clarify how parameters interact or typical use cases.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (update) and the resource (card) with specification that it's a saved question in Metabase. It is unambiguous but does not differentiate from sibling tools like create_card or delete_card.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., create_card for new cards, or other update tools). The description implies it is for updating existing cards, but lacks explicit context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It says 'Update' which implies mutation, but does not disclose any side effects, requirements (e.g., admin privileges), or whether it is destructive/irreversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, no redundancy, and directly states the purpose. However, given the complexity of the tool, it is slightly under-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, no annotations, and complex nested parameters, the description is severely lacking. It does not explain return values, error conditions, or the format of the permission mapping. The tool is incomplete for an agent to use reliably.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%. The description adds no explanation of the parameters (e.g., 'revision' and 'groups'). The nested 'groups' object is complex and the description gives no hints about its structure or usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it updates the collection permissions graph for groups and collections in Metabase. The verb 'update' and specific resource 'collection permissions graph' distinguish it from sibling tools like 'update_permission_group' or 'update_data_permissions'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'update_data_permissions' or 'update_permission_group'). No prerequisites or context about typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It only implies mutation ('update') but does not disclose required permissions, update semantics (partial vs full), side effects, or return value. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-front-loaded sentence with no fluff. However, it could benefit from additional structuring to highlight key parameters or usage notes.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With a nested input object, 4 effective parameters, no output schema, and no annotations, the description is far too minimal. It does not explain update semantics, which fields are updatable, or what the response contains, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% according to context, and the description fails to explain the 'input' object or its properties. Parameters like 'name', 'content', 'archived' are left completely undocumented beyond the schema itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and resource 'document by ID', distinguishing it from create, delete, get, and other siblings. However, it lacks specificity on which fields can be updated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like update_dashboard, update_card, etc. The description does not provide any usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only says 'execute'. No mention of side effects, permissions, rate limits, or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence and front-loaded, but it is too short to convey necessary details. Concise but incomplete.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and high complexity (pivot with parameters), the description is severely lacking. It does not explain return values, parameter usage, or constraints, making it inadequate for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description should compensate. It hints that the id parameter is a card ID but does not explain the optional parameters array or their semantics. The schema already describes the id, so little added value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'execute' and the resource 'card', specifying the pivot table mode. It distinguishes from siblings like 'execute_card' by mentioning pivot, though does not explicitly differentiate from other pivot tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as execute_card or execute_query_pivot. Lacks context for prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description must disclose behavior. It does not mention side effects (e.g., dashboard creation), permissions, or return format, leaving critical gaps for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but lacks structure. It does not front-load key differentiators or organize information for easy scanning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 required nested parameters and no output schema, the description is severely incomplete. It omits relationships between fields and the shape of the returned dashboard.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% per context, and the description adds no meaning to parameters. The nested 'input' object with 7 required fields is not explained, forcing reliance on the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets a comparison x-ray dashboard for a cell with a rule, differentiating from siblings like get_xray_entity_cell (no rule/compare) and get_xray_entity_compare (no cell/rule). However, 'automagic' is vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs. siblings like get_xray_entity_cell_compare or get_xray_entity_rule_compare. The context of many similar x-ray tools demands explicit usage hints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only repeats the name without disclosing read-only nature, permission needs, or pagination behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, no waste, but too brief to be useful. Front-loads the purpose but lacks structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations, and minimal description. The tool's behavior, response format, and filtering criteria are entirely unspecified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in schema (100% coverage). Baseline 3, description adds no extra meaning beyond the trivial empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a verb (list) and resource (popular items), but 'popular items' is vague and not differentiated from sibling list tools like list_recents or list_cards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Context signals show many list tools, but description provides no exclusions or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It says 'run a pivot query' but does not state whether this is read-only, what side effects exist, what authentication is needed, or what the response looks like. The word 'preview' might imply read-only, but it's not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single brief sentence, but it is under-specified. While it avoids verbosity, it sacrifices important information, making it insufficient for an agent to use correctly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested input, many sibling tools, no output schema, no annotations), the description is severely incomplete. It does not explain what a pivot query is, what 'preview embedded' means, how parameters relate, or what the tool returns. The agent lacks critical context to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%: the description does not mention any of the three required parameters (token, card_id, dashcard_id). The nested input object is completely unexplained. With zero coverage, the description fails to add any meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (run a pivot query) and the resource (preview embedded dashboard dashcard). The name itself is very specific, and the description aligns with it, distinguishing from siblings like run_preview_embed_dashcard_query (non-pivot) and run_embed_dashboard_pivot_dashcard_query (non-preview).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description provides no context about prerequisites, when a pivot query is needed, or how this differs from similar tools like run_preview_embed_dashcard_query. The agent is left to infer from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It only states the action but does not disclose if it is read-only, how search matches (exact, partial, etc.), or any side effects. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, making it concise but potentially too brief given the tool has three parameters and no output schema. It lacks structured details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has three required parameters and no output schema, the description is incomplete. It does not explain what the search returns, how to interpret results, or any constraints. An agent would lack sufficient context to use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the parameters beyond what the schema already provides. The schema has descriptions for inner fields, but overall schema description coverage is 0%, so the description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Search values for a dimension of a metric in Metabase', clearly indicating a search operation on metric dimension values. It distinguishes from sibling 'get_metric_dimension_values' which likely returns all values. However, it lacks precision about the return format or scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_metric_dimension_values' or other search tools. The description does not indicate prerequisites or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states the basic action. It does not disclose side effects, authentication requirements, rate limits, or idempotency, which are critical for a send operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but under-specified. It lacks structure and does not provide enough information to justify its brevity, given the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of sending a notification with an open schema (additionalProperties allowed), the description is severely incomplete. It omits details on channels, payload fields, response format, and error conditions, making it nearly useless for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a single parameter 'input' with a nested 'notification' object described as 'Notification payload to send ad-hoc'. The tool description adds no extra meaning beyond this vague schema, failing to clarify the payload structure or required fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies the verb 'send' and resource 'ad-hoc notification', clearly indicating the tool's action. The term 'ad-hoc' helps distinguish it from scheduled notifications, though it does not explicitly differentiate from the sibling 'send_notification'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'send_notification'. The description lacks context about prerequisites, scenarios, or exclusions, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It fails to disclose behavioral traits such as whether the operation is destructive, if a table name must be unique, permission requirements, or file size limits. 'Upload' implies mutability but no details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but omits critical details. It is under-specified for a tool with multiple parameters and no annotations. A slightly longer description with key behavioral notes would be more helpful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and 0% schema coverage, the description is severely incomplete. It lacks information about response format, file requirements, error handling, and constraints. The agent cannot reliably invoke this tool without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, requiring the description to compensate. It does not explain any parameter, including required fields like db_id and table_name, or optional ones like schema_name and collection_id. The input is a nested object, adding complexity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (upload), resource (CSV file), and outcome (create a new table in Metabase). It distinguishes from siblings like append_csv_to_table and replace_table_csv by specifying 'create a new table'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like append_csv_to_table or replace_table_csv. The description lacks when-not-to-use or context about prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It only states 'archive' without explaining behavioral impacts (e.g., reversibility, effect on queries, permissions required). This is insufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence is concise, but it lacks structure (e.g., no parameter guidance or usage notes). It is not overly long, but the brevity sacrifices completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, no annotations, and a simple parameter, the description should explain the archiving behavior and outcome. It fails to provide enough context for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite schema coverage being 0% per context, the description does not mention the 'id' parameter or its purpose, which the input schema already describes. The description adds no value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'archive' and the resource 'native query snippet' in Metabase, distinguishing it from siblings like delete_snippet. However, it does not specify what archiving entails (soft delete vs hard delete), leaving ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives like delete_snippet or create_snippet. There is no mention of prerequisites, context, or use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavior but only states the basic operation. It does not mention side effects (e.g., card removal from original collection), permissions required, or whether the action is reversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence efficiently conveys the core action, but is under-specified for a tool with nested parameters. Not verbose, but could add more without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity and no output schema, the description is incomplete. It omits return values, success/failure indicators, and constraints (e.g., maximum cards per move). The agent lacks information to safely invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description adds no explanation of parameters. It does not clarify that 'card_ids' are the IDs of cards to move or that 'collection_id' is the target, leaving meaning solely to property names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action (move) and resources (cards to a collection), but fails to distinguish from sibling tool 'move_cards_to_collection' which likely performs a similar action. The description does not clarify if this is bulk vs singular.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'move_cards_to_collection'. Missing context on prerequisites, efficiency benefits of bulk operations, or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose any behavioral traits such as whether updates are atomic, reversible, or what happens on partial failure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but merely restates the tool name, offering no additional structure or information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a bulk update operation and the absence of output schema or annotations, the description is severely lacking in providing complete context about behavior, error handling, or return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description adds no meaning beyond the input schema; the schema itself includes a description for the 'tables' parameter, but the tool description is silent on parameter details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (bulk update) and resource (multiple tables in Metabase), distinguishing it from single-table update tools like update_table.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., update_table, update_table_fields_order), nor any prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description should disclose behavioral traits like idempotency, side effects (e.g., triggering email delivery), or authorization needs. It only states 'Configure' without explaining if it creates, updates, or resets settings.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and to the point, but it sacrifices necessary detail for brevity. It is not overly verbose, but the lack of critical information reduces its effectiveness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the nested input schema and lack of output schema or annotations, the description is insufficient. It does not explain return values, the effect on the system, or confirm the operation's success.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not explain parameters beyond the schema, and schema description coverage is 0%. Although the input schema includes property descriptions, the tool description itself adds no value for parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool configures SMTP email settings in Metabase, using a specific verb and resource. It distinguishes from siblings like 'clear_email' and 'update_setting' by focusing on SMTP settings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as updating individual settings via 'update_setting' or clearing email settings via 'clear_email'. The description lacks context about prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It only says 'copy', which implies mutation but omits whether it creates a deep copy, what fields are copied, where the new document is placed, or if authentication is required. Critical missing details for a safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (7 words) but lacks essential information. Conciseness should be adequate, not under-specified. Every sentence should earn its place, but here it omits critical details, making it insufficiently informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and 0% schema description coverage, the description is severely incomplete. It fails to explain the copy behavior, side effects, permissions, or output, leaving the agent without enough context to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema defines one required parameter 'id' with description 'Source document ID'. The description mentions 'by ID', confirming the parameter's purpose but adds no extra semantic value beyond what schema already provides. Schema coverage is 0%, but the description aligns with the schema. Baseline for single param with minimal compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (copy) and resource (a document) with the method (by ID). It distinguishes from sibling tools like copy_card and copy_dashboard by specifying document. However, it does not clarify what type of document (e.g., Metabase document type) which could be ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like create_document or get_document. There is no mention of prerequisites, restrictions, or use cases. The agent cannot determine appropriate context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description 'Create a new API key' implies a write operation, but does not disclose side effects (e.g., key value returned, activation state, permissions needed). Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it concise. However, it is too terse and does not front-load useful information beyond what the name implies.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given one nested parameter, no output schema, and no annotations, the description should provide more context (e.g., what happens after creation, any restrictions). It is incomplete for safe usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention or explain parameters. Although the input schema includes property descriptions ('Name of the API key', 'ID of the permission group'), the tool description adds no value for parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and the resource ('API key') and context ('Metabase'). It distinguishes from siblings like 'regenerate_api_key' and 'delete_api_key' by the verb, but does not elaborate on the resource's role.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., regenerate_api_key vs update_api_key). No prerequisites like needing a permission group ID are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states 'Create a new pulse', without disclosing side effects, required permissions, or constraints (e.g., data validation, duplicate handling, creation limits). This leaves significant behavioral details undisclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it concise. However, it is overly minimal and could be more informative without adding significant length. It is not wasteful, but it also does not fully utilize its space.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested required parameters, no output schema, no annotations), the description is insufficient. It lacks guidance on what a pulse is, how to structure the input, what the tool returns, and under what conditions it might fail. This leaves the agent without enough context to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the parameters. The single parameter 'input' is an object with nested required fields (name, cards, channels), but the top-level parameter lacks a description. Schema description coverage is 0%, so the description should compensate, but it does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource ('Create a new pulse in Metabase'), clearly indicating the tool's function. However, it does not differentiate from other create tools (e.g., create_card, create_dashboard) beyond the resource name, and assumes the user knows what a 'pulse' is.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like create_card or create_dashboard. There are no prerequisites, exclusions, or context about appropriate use cases, leaving the agent without decision support for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits (e.g., side effects, required permissions, error conditions). The minimal description does not address these, leaving the agent uninformed about core behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence), which is efficient but insufficient for a complex tool with nested input. It front-loads the purpose but omits essential details, making it under-informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested required input, no output schema, no annotations), the description is far from complete. It does not explain the segment concept, MBQL format, or what the tool creates, leaving significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for parameter meaning. However, the description adds no value beyond the schema's own property descriptions (which exist but are not counted). It fails to explain what 'definition' in MBQL format means or how to construct it, relying entirely on the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create a new segment in Metabase' clearly states the action (create) and resource (segment). It is specific and unambiguous, though it does not differentiate from sibling creation tools like create_measure or create_dashboard, which is acceptable given the unique resource name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., update_segment or other creation tools). The description lacks any context about prerequisites, input format, or intended use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It only states that it creates an event, without disclosing any side effects, required permissions, or success/failure outcomes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded. However, it is too minimal and lacks detail that could be added without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex input with required nested fields and no output schema, the description is insufficient. It does not explain what happens after creation or any other contextual details that would help an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (though the schema itself contains descriptions). The tool description does not add any parameter meaning beyond 'Create a new timeline event'. The nested object parameters are left unexplained in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create a new timeline event in Metabase' clearly states the verb (create) and resource (timeline event). It is specific to the tool's action, though it does not differentiate from sibling tools like 'create_timeline' or 'update_timeline_event'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'create_timeline' or 'update_timeline_event'. The description lacks context on prerequisites or scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only says 'create' with no disclosure about side effects, duplicate email handling, authentication requirements, or rate limits. With no annotations, the agent lacks critical behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it sacrifices clarity and completeness. It is front-loaded but lacks structured details that would help the agent understand the parameters or usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema, required fields, and lack of annotations or output schema, the description is insufficient. It does not cover optional fields like password or group_ids, nor does it explain the return value.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. The 'input' object is not described, and the schema's property descriptions are not referenced. The 0% schema coverage at the top level is not compensated.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (create) and resource (user) and context (Metabase), distinguishing it from sibling tools like create_action or create_api_key. However, it lacks specificity about the required fields and optional parameters, which would make it clearer.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other user-related tools (e.g., update_user, delete_user) or any prerequisites. The agent has no context on scenarios like SSO setup or permission group assignment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description only says 'Delete a timeline by ID'. It does not disclose destructive effects, irreversibility, cascading deletions, permission requirements, or side effects. For a mutation tool without annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no extraneous words. However, it is terse to the point of missing important context, balancing conciseness against completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's destructive nature, lack of output schema, and minimal description, it is incomplete. The agent gains no insight into return values, side effects, or post-deletion state, making it inadequately specified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the 'id' parameter as 'ID of the timeline to delete'. The tool description adds no additional meaning beyond what the schema provides. With schema description coverage listed as 0%, the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Delete' and the resource 'timeline', specifying the identifier 'by ID'. While it distinguishes the resource from siblings (e.g., delete_timeline_event), it does not explicitly contrast with other delete tools, but the resource specificity is sufficient.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like delete_timeline_event. No prerequisites, context, or exclusions are provided, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a mutation (dismissing a modal) but does not disclose side effects, idempotency, permissions required, or any behavioral traits. With no annotations, the description carries the full burden and fails to provide adequate transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, very concise. However, it sacrifices completeness for brevity, which is acceptable but not ideal. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of output schema and annotations, the description is incomplete. It does not explain what happens after dismissing, possible errors, or any return value. The nested object parameter further increases complexity, yet no details are provided.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning to the parameters. The schema has 0% description coverage and does not explain 'id' or 'modal' meaning. The tool description does not compensate, leaving the agent to guess parameter purposes.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'dismiss', the resource 'modal', and the context 'for a user in Metabase'. It is specific and likely distinguishes this tool from siblings, though it could specify which modals are affected.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, typical use cases, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of disclosure. It states it 'return the query results' but does not indicate whether the operation is read-only or has side effects, nor does it mention permissions, rate limits, pagination, or output format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks necessary detail. It is front-loaded but insufficient for a tool with a nested input schema and many siblings.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested input, many sibling tools, no output schema), the description is incomplete. It misses return value details, usage examples, and context for parameter usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for both parameters (id and parameters), but the tool description adds no value beyond what the schema already provides. Given 0% schema coverage, the description should compensate, but it does not explain how to use the parameters or their types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool executes a card (saved question) and returns query results. It uses a specific verb and resource, distinguishing it from related sibling tools like execute_query or execute_card_pivot, though it does not explicitly differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as execute_query, execute_card_pivot, or export_card_query. There is no mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description fails to disclose behavioral traits such as authorization requirements (public access), side effects, or rate limits. It only states the action without context about what happens during execution.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 11 words, concise but under-specified. It does not waste words, but fails to convey necessary details, especially for a tool with many peers.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and the presence of many sibling tools, the description is incomplete. It does not explain the purpose beyond the obvious, nor does it address the specific format or how this tool differs from similar export tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage (only field names and types are given). The description adds no meaning to parameters like 'export_format' (possible values), 'uuid', 'dashcard_id', or 'card_id'. An agent would need external knowledge to use them correctly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it exports results of a public dashboard card query in a specific format. It includes a verb and resource, but does not differentiate from siblings like export_public_card_query or export_dashcard_query. The title is null, further reducing clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus the many similar export tools. There are no when-to-use, when-not-to-use, or alternative suggestions, making it hard for an agent to select correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits like idempotency (read-only), authentication requirements, or error handling. It only states the basic action, which is insufficient for an agent to understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (8 words) and front-loaded with the verb and resource. However, it may be too minimal to provide sufficient context; it earns its place but could include more value without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should clarify what information is returned (e.g., full database object with settings, tables, etc.) and any prerequisites (e.g., database must exist). The current description only states the action, making it incomplete for safe agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The parameter id is documented in the schema as 'Database ID', but the tool description does not elaborate on its meaning, format, or constraints. Given the 0% schema coverage metric, the description should compensate but fails to do so, leaving agents to rely on the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the verb 'Get' and identifies the resource 'a single database' with method 'by ID'. It is clear and specific, but does not differentiate from sibling tools like get_database_metadata or list_databases, limiting its score to 4.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as list_databases or get_database_metadata. An agent could benefit from knowing that this tool returns the complete database object, while others return specific aspects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must fully disclose behavioral traits. It states 'Get' implying a read operation, but does not explicitly confirm idempotency, permission requirements, side effects, or output structure. Minimal behavioral context beyond the verb.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with the action and resource, no extraneous words. Perfectly concise for a simple tool, though it sacrifices completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema, lack of output schema, and no parameter descriptions, the description is woefully incomplete. It fails to define 'remapping', describe return values, or provide usage context, making it inadequate for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, meaning the description must compensate, but it adds no parameter meaning. The tool description does not explain what 'parameter' or 'field_ids' mean or how they relate to remapping, leaving the agent to infer from parameter names alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (get) and resource (remapping for a dataset parameter), but does not differentiate from similar sibling tools like get_card_param_remapping or get_dashboard_param_remapping. It provides a specific verb+resource combination, earning a 4.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., get_card_param_remapping). The description is context-agnostic, leaving the agent without decision criteria. The sibling list shows many similar tools, and the description offers no exclusions or when-not-to-use advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral traits such as read-only nature, required permissions, side effects, or return format. The name implies read-only, but this is not confirmed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence), but it lacks essential information, making it under-specification rather than efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex nested parameter and lack of output schema or annotations, the description is insufficient. It does not explain what metadata is returned or how to structure the query, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explain the 'input' parameter or the 'query' object within it. With 0% schema coverage, the description should clarify what constitutes a valid query (e.g., native SQL vs MBQL), but it fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('get metadata') and resource ('dataset query'), but does not differentiate it from sibling tools like get_card_metadata or get_dashboard_metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as get_card_metadata or get_database_metadata. The context of 'dataset query' is not explained.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It states it 'gets query results' but does not indicate whether the operation is read-only, what happens on invalid tokens, rate limits, or whether it returns raw data or triggers downloads. This is insufficient for safe agent decision-making.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that efficiently conveys the main purpose. It is front-loaded with key information, but could include more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex nested parameter structure, lack of output schema, and many similar sibling tools, the description is incomplete. It does not explain the return format (e.g., file content vs. URL) or provide context about the embedding mechanism, leaving the agent uncertain about behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description adds no parameter-level meaning. The nested 'input' object is not explained, and the parameter descriptions ('JWT embed token', 'Export format') are minimal. The description fails to compensate for the absent schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('get'), the resource ('query results for an embedded card'), and a qualifier ('in a specific export format'), making the purpose specific and unambiguous. However, it does not explicitly differentiate from closely related siblings like get_embed_card_query or export_embed_card_query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the many similar sibling tools (e.g., get_embed_card_query, export_embed_card_query). It lacks any when/when-not information or prerequisites, forcing the agent to rely solely on the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as side effects, security requirements (beyond the JWT token), or whether the operation is read-only. The description is too minimal to offer transparency about the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a single sentence, but it is overly brief. Important information (e.g., what the response contains) is omitted. It could be expanded without losing conciseness to include key details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of output schema and annotations, the description is insufficient. It does not explain what the tool returns (e.g., a JSON dashboard object or HTML), which is essential for an agent to understand the outcome. The complexity of the Metabase API warrants a more complete description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage for the parameter 'token'. The description adds that the token is a JWT token from Metabase, which is basic. No additional details about format, validity, or constraints are provided, so it only marginally adds value over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Get' and the resource 'embedded dashboard', specifying the use of a JWT token. It distinguishes itself from sibling tools like 'get_embed_card' by focusing on dashboards. However, it does not specify what exactly is returned (e.g., dashboard data, HTML), leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus other related tools such as 'get_embed_dashboard_query', 'get_embed_dashboard_tile', or 'get_embed_dashboard_params'. An agent lacks context to differentiate among them, which is critical given the many sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose any behavioral traits beyond the action. It does not mention authentication requirements, idempotency, side effects, or output format, which is necessary for a tool with no schema descriptions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a single sentence, but it lacks structure. It could be more useful with additional context about input/output, but it is not overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, and the complexity of param remapping with many sibling tools, the description is incomplete. It does not explain what remapping does, prerequisites, or result format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema requires 'token' and 'param_key', but neither parameter is described in the schema (0% coverage) nor in the description. The description adds no meaning to these parameters, leaving the agent to guess their significance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'remapping for a parameter of an embedded dashboard', which is specific. However, it does not differentiate from sibling tools like 'get_dashboard_param_remapping' or 'get_embed_card_param_remapping', which have similar purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. With many sibling param remapping tools, the description should mention what distinguishes this from others, such as the fact that it operates on embedded dashboards specifically.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fails to disclose behavioral traits such as read-only nature, authentication requirements, or any side effects. The minimal description leaves the agent unaware of important context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is efficiently front-loaded with the verb and resource. It is concise, though it could include more useful context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and the nested parameters, the description is incomplete. It does not specify the return format or structure, leaving the agent to guess what the tool returns. Additional context is needed for safe invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. While the nested parameters have descriptions in the schema, the tool-level description does not explain the parameters at all. Schema coverage is 0% for top-level parameters, so the description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves values for a parameter in an embedded dashboard from Metabase. However, it does not distinguish from sibling tools like `get_embed_dashboard_param_values` or `search_embed_dashboard_params`, which have similar purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not indicate when to use this tool versus alternatives, nor does it mention prerequisites like obtaining a valid embed token.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior but only states a read operation. It fails to mention what happens if the token is invalid, the format of returned values, or any side effects. The behavioral profile is insufficiently described.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no redundancy. However, it is too brief and could be better structured to include context about usage or parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, plus the minimal description, the tool definition is incomplete. It does not explain the response format, error conditions, or how to construct the input correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, and the description adds no meaning to the parameters. It does not explain what 'param_key' refers to (e.g., name vs. ID), or provide examples or formats. The description fails to compensate for the lack of schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the verb 'Get' and the resource 'values for a parameter of an embedded dashboard'. However, it does not differentiate from sibling tools like 'get_embed_dashboard_params' or 'search_embed_dashboard_param_values', which may have overlapping functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, use cases, or exclusions, leaving the agent to infer context from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It merely states 'get details', implying a read operation, but lacks specifics about authentication, rate limits, or what constitutes 'details'. The description is too minimal to provide adequate transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with a single sentence that front-loads the purpose. However, it is too sparse, failing to provide essential context. It earns a 3 as it is efficiently short but lacks necessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (1 parameter, no output schema), the description is incomplete. It does not specify what 'details' includes, nor does it differentiate from the many sibling field tools (e.g., get_field_related, get_field_summary). The context of the Metabase API is present, but not sufficiently leveraged.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, so the description should compensate by explaining the parameter. It only mentions 'by ID', which is already implied by the schema's required 'id' field. The schema itself has a description 'Field ID' for the property, so the tool description adds no extra meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', resource 'field', and the source 'Metabase'. It conveys the basic purpose of retrieving field details by ID. However, it does not differentiate from sibling tools like get_field_related or get_field_summary, which reduces clarity in a context with many similar tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives. It does not provide any context about prerequisites, limitations, or when not to use it. The description offers no comparative information despite many sibling field-related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as idempotency, required permissions, or side effects. It merely states the action without additional context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence) but lacks detail. It is appropriately sized for a simple fetch tool but could include more context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and lack of output schema, the description is insufficient. It does not explain what the remapping is or what the response contains.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add meaning beyond the input schema. With 0% schema coverage reported, the description should compensate but it does not explain the parameters further.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Fetch') and the resource ('remapping for a dimension value of a measure'), but it does not differentiate from similar sibling tools like 'get_metric_dimension_remapping'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, exclusions, or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It only states 'Fetch values,' but does not indicate whether the operation is read-only, requires permissions, has side effects, or details about pagination or response format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at one sentence with no unnecessary words. However, it is too brief and could be expanded to include key usage information without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with a nested input object, two required parameters, no output schema, and no annotations, the description is insufficient. It does not clarify how to use the parameters, what the return values look like, or how it relates to sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has descriptions for both parameters ('Measure ID' and 'Dimension key of the measure'), but the description adds no additional meaning. Given the schema description coverage is 0% (per context), the description fails to compensate by explaining what a 'dimension key' is or how to obtain it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the verb 'Fetch' and identifies the resource as 'values for a dimension of a measure' in Metabase, which is clear. However, it does not distinguish this tool from siblings like get_metric_dimension_values or search_measure_dimension_values, which have similar purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as search_measure_dimension_values or get_measure_dimension_remapping. There is no mention of prerequisites, use cases, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states 'Fetch', implying a read-only operation, but does not mention important traits like pagination, rate limits, error handling, or what happens if the dimension does not exist. This is insufficient for an agent to safely invoke the tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it omits essential details. It does not front-load critical information like output format or parameter constraints. The brevity here is not an asset because it sacrifices completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, no annotations, and minimal parameter descriptions. The description does not explain what values are returned, how to interpret them, or handle edge cases. Given the complexity of the domain (Metabase metrics and dimensions), this description is inadequate for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has two parameters with minimal descriptions ('Metric ID', 'Dimension key of the metric'), and the tool description adds no additional meaning. Given 0% schema description coverage, the description should compensate but does not. It does not explain how to obtain the 'dimension_key' or provide examples.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Fetch' and resource 'values for a dimension of a metric', indicating a read operation. However, it does not distinguish from the sibling tool 'search_metric_dimension_values', which likely serves a similar purpose with different filtering capabilities. A score of 4 reflects clarity but lack of differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives like 'search_metric_dimension_values' or 'get_metric_breakout_values'. The description provides no context for appropriate usage scenarios, prerequisites, or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It implies a read operation ('get') but does not disclose any behavioral traits such as authentication needs, rate limits, or return format. Minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short (one sentence) and front-loaded, but it lacks substance. It is concise but not sufficiently informative for a tool with nested parameters and no annotations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has nested objects, no output schema, and no annotations, the description is incomplete. It does not explain what a 'remapping' is, what the response contains, or any dependencies.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% per context (though the schema itself has brief descriptions for token and param_key). The description adds no parameter explanation beyond what the schema provides, leaving the agent to rely solely on parameter names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Get remapping for a parameter of a preview embedded card', clearly indicating the verb ('Get') and resource (remapping for a preview embedded card parameter). However, it does not distinguish from the sibling tool 'get_embed_card_param_remapping', which is identical except for 'embed' vs 'preview embed'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., get_embed_card_param_remapping for actual embeds). No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose behavioral traits such as auth requirements, rate limits, or whether the operation is read-only. The description merely states the action without behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the purpose. It is appropriately sized but could be slightly more concise. No unnecessary words are present.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a nested input schema and no output schema. The description does not explain what the return values look like, any pagination, or ordering. For a tool that retrieves parameter values, this lack of context hinders proper usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not add any meaning to parameters. The parameters 'token' and 'param_key' are left unexplained beyond their names, failing to clarify format, source, or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the verb 'Get' and the resource 'values for a parameter of a preview embedded card', which is specific. However, it does not differentiate from similar siblings like 'get_embed_card_param_values' or 'search_preview_embed_dashboard_param_values', limiting clarity on the exact scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Given many siblings with similar param value retrieval (e.g., get_embed_card_param_values, search_preview_embed_dashboard_param_values), the description lacks context on distinguishing use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose any behavioral traits such as read-only nature, authentication requirements, rate limits, or side effects. It only states the purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it omits critical information. It is front-loaded but too minimal for the complexity of the tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the single parameter with nested objects, no output schema, and no annotations, the description is incomplete. It does not explain what 'remapping' means or what the response contains.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%. The description does not explain the parameters 'uuid' and 'param_key', nor the nested structure. The parameter semantics rely entirely on the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'remapping for a parameter of a public card'. However, it does not differentiate from siblings like get_card_param_remapping or get_embed_card_param_remapping.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_card_param_remapping (for non-public cards). No context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It only states the action without mentioning authentication needs, read-only nature, or what 'related items' includes. The schema adds an id parameter, but the description adds no behavioral context beyond the basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise. However, it is too minimal; it could include more information without being wordy. It earns its place but lacks structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested parameter, no output schema, no annotations), the description is incomplete. It does not explain what 'related items' are, the format of the response, or any prerequisites. Among many sibling tools, it provides insufficient context for an agent to select it confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add meaning beyond the schema. The schema has a nested 'input' object with an 'id' property described as 'The segment ID'. With schema description coverage at 0% (no descriptions for the top-level parameter), the description fails to explain the nested structure or any constraints on the id value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get related items for a segment in Metabase' clearly states the verb (Get) and resource (related items for a segment). It distinguishes from siblings like get_segment (which retrieves the segment itself) and get_segment_revisions. However, it does not specify what kind of related items are returned.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like get_field_related, get_table_related, or get_dashboard_related. No context about prerequisites or scenarios is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for behavioral disclosure. It only states 'Get' which implies a read operation, but omits details on idempotency, authentication requirements, rate limits, or side effects. A 2 is appropriate given the absence of crucial behavioral clarity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but lacks necessary detail. It is front-loaded with the verb and resource, but the brevity results in insufficient information for an agent. A score of 3 reflects that it is minimally adequate but not well-structured for completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the single parameter and lack of output schema, the description should provide more context. It fails to explain what 'table' means in this context (definition vs. data), how it differs from similar tools, or what the response contains. The completeness is poor for a tool with many siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is indicated as 0% (though the schema actually has a description for 'id'). The tool description does not add any meaning beyond the schema. The nested 'input' object and required 'id' parameter are not elaborated upon, leaving the agent without additional context on the parameter's role.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and resource 'single table by ID from Metabase'. It distinguishes from siblings like get_table_data, get_table_metadata, and list_all_tables by focusing on a single table retrieval. However, it does not specify whether it returns the table definition or its data, which could cause ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_table_data, get_table_metadata, or list_all_tables. The description lacks any context on prerequisites, typical use cases, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for disclosure. It only states a read operation ('get') but omits any details about side effects, authentication requirements, rate limits, or safety. This is insufficient for a tool that may require specific permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at one sentence. It is front-loaded and free of fluff. However, the brevity sacrifices necessary detail, which is a trade-off that reduces its helpfulness slightly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter) but lack of output schema and annotations, the description should provide more context about return format or usage patterns. It does not help the agent understand what to expect or how to integrate this tool into a workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning to the 'id' parameter beyond what is in the schema. Schema coverage is 0%, and the description fails to explain how to specify the table or any additional context. The nested object structure is not clarified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('get') and the resource ('foreign keys for a table'), making the purpose obvious. However, it does not explicitly distinguish this tool from sibling tools like get_table_metadata or get_table_related, which might also return related information.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor are there any prerequisites or exclusions mentioned. The agent receives no help in deciding if this tool is appropriate for the current task.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states what it does but not whether it's read-only, permission requirements, side effects, or response format. The word 'Get' implies a read operation, but explicit confirmation is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but under-specified. It front-loads the purpose but sacrifices necessary detail. It could be expanded with minimal extra text to cover usage and parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a nested object parameter, no output schema, and many siblings. The description does not explain the return value or differentiate from similar metadata tools. It is incomplete for an AI agent to decide when to use it and what to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description does not mention parameters at all. It fails to add meaning beyond the schema, which ironically contains basic descriptions like 'Table ID'. The tool description should clarify the purpose of the 'include_hidden_fields' parameter and why it matters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns table metadata including fields. It distinguishes itself from likely related tools like 'get_table' (which may return the table object) and 'get_table_data' (which returns data). However, it does not explicitly differentiate from other metadata tools like 'get_table_foreign_keys' or 'get_table_related'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs. alternatives. With many sibling tools for table-related operations, the description should indicate the specific use case (e.g., retrieving field-level metadata) and when not to use it (e.g., for table data or foreign keys).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose any behavioral traits like idempotency, error conditions, or authentication requirements. The minimal description fails to inform the agent about potential side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks structure and additional context. It prioritizes brevity over completeness, omitting important details like output expectations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and many sibling tools, the description does not provide enough context for an agent to use the tool correctly. It fails to describe the return value or distinguish the tool from similar 'get' operations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0% (context indicates low coverage), and the description only repeats that the tool uses an ID. It adds no information about the ID format, valid values, or how to obtain it, offering no value beyond the schema's 'Task ID'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), resource ('scheduled task'), and identifier ('by ID'), making the tool's primary purpose evident. However, it does not differentiate from siblings like 'get_task_info' or 'get_task_run', which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'list_tasks' or 'get_task_run'. An agent would not know which tool to choose for different scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It does not disclose read-only nature, authentication needs, or what 'automagic' entails. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, 11 words, concise but too terse to adequately describe the tool. Front-loaded but insufficient detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has complex input (nested object, enum, no output schema, no annotations). Description only tells what it does, not how output looks, prerequisites, or effect. Incomplete for safe invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has one nested parameter with enum and required fields, but description adds no meaning beyond schema. 'Any entity' is broader than schema's 5 types, potentially misleading. Zero schema description coverage demands more from description, which is lacking.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves an x-ray dashboard for an entity, with a specific verb and resource. However, 'automagic' is vague and doesn't differentiate from sibling x-ray tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other get_xray or get tools. No when-not-to-use or alternative tools mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description implies a read-only operation ('Get') but does not disclose behavior such as required permissions, return format, or side effects. Minimal transparency beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 13 words, very concise. It is front-loaded with the key verb and object. However, it could be expanded with brief parameter context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations. The description is too brief to provide complete context for a tool with a nested parameter structure. It does not explain what 'query metadata' entails or what the return values are, leaving the agent without enough information to understand the tool's full behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% per context signals, and the tool description adds no information about parameters. The description lacks any parameter details, failing to compensate for low schema coverage. The schema itself has descriptions, but the tool description does not reinforce or clarify them.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('query metadata for an x-ray automagic dashboard entity'). It distinguishes from sibling tools like get_xray_entity by specifying 'query metadata', though 'automagic' is informal and could be clarified.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description does not mention prerequisites, context, or situations where this tool is appropriate compared to other x-ray or metadata tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It implies a read operation but does not explicitly state that it is read-only, safe, or whether authentication is required. No mention of pagination or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. However, it omits the optional filter parameter, which would improve utility without adding much length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, and only one optional parameter, the description is insufficient. It does not explain the return format, pagination, or any additional context needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema description coverage is 0%, and the tool description does not add any meaning beyond the schema. The description fails to mention the optional 'namespace' filter, which is crucial for filtering. The description should compensate for the low schema coverage but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets a list of all collections, with the parenthetical '(folders)' adding context. It differentiates from sibling tools like 'get_collection' (single) and 'create_collection', but could be more specific by mentioning the optional namespace filter.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'get_collection' for a specific collection or 'search' for searching collections. There is no mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations and a minimal description, the tool's behavioral traits are not disclosed. The agent learns nothing about side effects, authentication needs, pagination, or what the list contains. The description adds no value beyond the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short, consisting of a single sentence with no fluff. However, it is under-specified to the point of being unhelpful. Conciseness is good, but structure and completeness are lacking.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, annotations, and the presence of sibling tools, the description is incomplete. It does not mention return types, pagination, or any filters beyond the parameters. A more complete description would include what notifications are included and how to interpret results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explain the parameters or their purpose. Although the input schema has descriptions for 'archived' and 'dashboard_id', the tool description itself adds no context. With 0% schema coverage in the description, the agent must rely solely on the schema, which is insufficient for correct usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Get list of notifications from Metabase', which clearly identifies the action (list) and resource (notifications). However, it does not differentiate from sibling tools like 'get_notification' or 'list_alerts', which could cause confusion about which tool to use.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description lacks any mention of context, prerequisites, or when not to use it, leaving the agent without direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure, but it only states the action without any mention of safety (read-only?), performance, or return format. This is insufficient for a tool with zero annotation support.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, appropriately concise for a tool with no parameters. It is front-loaded and free of waste, though it could benefit from a second sentence to clarify scope.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the tool being simple (no parameters), the description lacks completeness. There is no output schema, and it fails to describe what the response contains or how 'unique' is defined, leaving the agent without critical details for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so the baseline is 4. The description adds no additional parameter information, but this is acceptable given no parameters exist. It does not hinder usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it lists unique tasks in Metabase, providing a clear verb and resource. However, it does not clarify what 'unique' means or differentiate from similar sibling tools like 'list_tasks' or 'list_task_runs', leaving the purpose somewhat vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no guidance on when to use this tool versus alternatives. No exclusions, prerequisites, or context for when 'unique tasks' would be relevant is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description lacks disclosure of destructive behavior (old key becomes invalid) or any side effects. Without annotations, the agent cannot assess the risk of this mutation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, very concise. However, it lacks structure and could benefit from bullet points or clearer phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not explain what happens after regeneration (e.g., returns new key) or any required permissions. For a mutating tool with no output schema, more context is essential.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the tool description provides no additional meaning for the 'id' parameter. The agent gets no help understanding what ID to provide or how it is used.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (regenerate) and resource (API key), but does not elaborate on what regeneration entails, such as revoking the old key and creating a new one. This is still specific enough to distinguish from create_api_key and update_api_key.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus create_api_key or update_api_key. It does not mention prerequisites or typical use cases, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits, but it only states the basic action. It does not mention side effects, authentication requirements beyond the token parameter, or error handling, leaving the agent with insufficient understanding of the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that efficiently conveys the core purpose. While very concise, it could benefit from a bit more context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema and lack of output schema or annotations, the description is incomplete. It fails to explain what a pivot query entails, how the token is used, or what the response contains, leaving significant gaps for an agent to fill.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage for its properties, and the tool description adds no explanation for the token, card_id, or dashcard_id parameters. The agent must infer their meaning from field names alone, which is insufficient for reliable invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (run a pivot query) and the resource (embedded dashboard dashcard in Metabase). However, it does not differentiate from closely related sibling tools like run_embed_dashcard_query or run_embed_card_pivot_query, which could lead to confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. Given many siblings with similar names, the description lacks context on when a pivot query is appropriate or what distinguishes it from other query execution tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It does not disclose safety traits (e.g., read-only, required permissions) or side effects. The name implies public access but is not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but under-specified. It lacks necessary details, making it inadequate rather than efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Missing output schema, no explanation of what a pivot query returns or what the parameters represent. For a 3-parameter nested input, this description is completely inadequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description does not explain the meaning of the 'input' object's properties (uuid, dashcard_id, card_id). No value added beyond schema structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Run' and resource 'pivot query for public dashboard dashcard'. Name is explicit and distinguishes from sibling tools like 'run_public_dashcard_query' and 'run_public_card_pivot_query'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'run_public_dashcard_query' for non-pivot, 'run_public_card_pivot_query' for cards). No prerequisites or when-not-to-use information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'Update' without detailing side effects, required authorization, or whether the key is immediately active. This is insufficient for a mutation operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise but lacking important details. It could be improved by adding a second sentence about updatable fields or constraints.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and the presence of sibling mutation tools, the description is incomplete. It does not explain return values, error conditions, or the scope of updates. A more complete description would clarify what can be updated and the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention the two parameters ('id' required, 'name' optional) or their roles. Although the input schema itself contains descriptions for both parameters, the tool description adds no value beyond what the schema provides. Given that schema description coverage is 0% (per context), it fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Update') and the resource ('API key') within the context of Metabase. It distinguishes from sibling tools like create_api_key, delete_api_key, and list_api_keys.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., regenerate_api_key for key rotation) or any prerequisites (e.g., admin permissions).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Absent annotations, the description must disclose behavioral traits. It only states 'Update', which implies mutation, but does not specify required permissions, side effects, idempotency, or whether changes are reversible. This lack of transparency hinders correct usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words, achieving brevity. However, it is overly terse and lacks structure (e.g., bullet points or sections). It could be expanded without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (multiple optional fields, collection_id with null option) and lack of annotations or output schema, the description is insufficiently complete. It omits behavior details, parameter guidance, and return information, leaving significant gaps for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter information beyond what the input schema already provides (schema description coverage is 0%). The schema itself has descriptions for id, name, description, and collection_id, but the description does not enhance or contextualize these. With low coverage, the description should compensate but fails.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'existing dashboard in Metabase', making the purpose unambiguous. It distinguishes from sibling tools like create_dashboard or copy_dashboard, but lacks specificity about which attributes can be updated, preventing a higher score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives such as create_dashboard or save_dashboard. The description does not mention prerequisites, context, or exclusions, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only says 'update', which implies mutation, but does not clarify if the update is partial or full, whether it requires specific permissions, or what the response looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence), but it is under-specified for the tool's complexity. While it is not verbose, it sacrifices necessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one nested parameter, no output schema, and no annotations, the description is extremely incomplete. It fails to explain what aspects can be updated, that only the name is modifiable, or that the ID must be provided.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% according to context, and the description adds no parameter information. The input schema itself has minimal descriptions ('Permission group ID', 'New permission group name'), but the description does not enhance understanding of parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Update' and resource 'permission group', clearly indicating what the tool does. It distinguishes from siblings like create_permission_group and delete_permission_group.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as when to use update_membership or delete_permission_group. It does not mention prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only says 'Update', implying mutation, but fails to mention whether permissions are required, if weights are replaced or merged, or if reindexing is triggered. No behavioral details beyond the mutation intent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but under-specified. It conveys the core purpose but sacrifices necessary detail. It earns its place but could be expanded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's nested input schema, no output schema, and no annotations, the description is extremely incomplete. It fails to explain how weights work, the range of values, allowed model types, or the effect of the update. This is insufficient for correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description adds no information about the parameters. The 'weights' object is explained only in the schema property descriptions (not in the description), leaving the agent without semantic context for what model types or weight values are valid.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool updates search result ranking weights in Metabase, using a specific verb ('Update') and resource ('search result ranking weights'). It distinguishes from siblings like 'get_search_weights' and 'reinit_search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as when to update weights versus reinitializing search. There are no prerequisites or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only implies a write operation but fails to state idempotency, error handling, or the requirement of revision_message for tracking.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded with the verb and resource. However, it is too brief and omits important details, making it minimally adequate.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input schema and many sibling tools, the description lacks details about required fields (id, revision_message) and does not explain the update process. The output schema is absent, leaving return values unclear.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (top-level 'input' has no description). The tool description adds no parameter meaning beyond what the schema provides, and does not compensate for the lack of top-level parameter description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'segment', and it distinguishes from siblings like create_segment or delete_segment. However, it could specify what aspects can be updated (e.g., name, definition).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives (e.g., create_segment for new segments). No prerequisites or conditions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only states 'Update Slack integration settings' but does not disclose any behavioral traits such as whether it overrides or merges settings, required permissions (beyond Pro licensing), rate limits, or consequences. No annotations are provided to supplement.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence + prerequisite). It is front-loaded with the prerequisite but lacks additional helpful context. It could be more informative without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and a complex required 'input' object, the description is inadequate. It does not explain return values, side effects, or how to use the parameters. A more complete description is needed for safe usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about parameters. The input schema provides descriptions for each sub-field (e.g., 'Slack bot token for integration'), but the tool description itself is silent on how to structure the 'input' object. Schema description coverage for top-level param is 0%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and resource ('Slack integration settings in Metabase'). It distinguishes from generic sibling 'update_setting' by specifying Slack. However, it does not explicitly differentiate from potential other Slack-related tools like 'send_slack_bug_report'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The only hint is the prerequisite '[Requires Metabase Pro]', but no context on when not to use or what to use instead if Pro is not available.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full behavioral disclosure. It does not mention side effects, authentication needs, or whether duplicates are allowed. A write operation with no behavioral context is problematic.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words. Front-loaded with verb and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and a nested parameter, the description lacks context about what happens after adding, how to view the activity, or error conditions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema already provides descriptions for model_type and model_id. The tool description adds no additional parameter meaning, and schema coverage is effectively provided by the schema itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'Add an item to recent activity', which is clear but generic. It does not specify what 'recent activity' represents or how it's used, leaving ambiguity compared to related tools like list_recents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like create_bookmark or list_recents. No context about prerequisites or typical scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states 'Perform initial Metabase setup', which implies a mutating operation but lacks details on what changes are made, required permissions, side effects, or whether it can be run multiple times. Behavioral insights are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no extraneous information. It is front-loaded and efficient. However, it could be slightly expanded without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a setup operation (likely involving user creation, token validation, preferences, database connection), the description is too sparse. No output schema or behavioral details are provided, and parameter semantics are not explained. The tool's role in the overall workflow is unclear.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no information about the single input parameter or its nested fields (token, user, prefs, database). The schema itself describes these fields, but the description offers no added meaning or context about how to use them. With 0% schema description coverage for the top-level parameter, the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Perform initial Metabase setup' clearly identifies the tool's purpose as a setup action for Metabase. It distinguishes from sibling tools (e.g., create_card, create_database) by specifying 'initial setup' rather than creating a specific entity. However, it could be more precise about what 'setup' entails.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. Among many create_* siblings, there is no indication that this is a one-time setup or prerequisites. No when-not-to-use or exclusion criteria are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses a destructive action (Delete) but fails to specify traits such as permanence, cascading effects (e.g., removing reactions), required authentication, or error handling. With no annotations, the description should provide more behavioral detail, but it is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that conveys the core purpose without extraneous words. However, it could be improved by including essential behavioral details without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive tool with no annotations or output schema, the description is incomplete. It lacks information about return values, success/failure indications, permissions, and side effects. While the tool is simple, more context is needed for safe usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add meaning beyond the input schema. The sole parameter 'id' is described in the schema as 'Comment ID to delete', but the tool description offers no additional context (e.g., how to obtain the ID). Given the low schema description coverage (0%), the description should compensate, but it does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Delete) and resource (comment) with the context 'from Metabase'. It is specific and distinguishable from sibling tools like create_comment or update_comment, though it does not elaborate on what types of comments (e.g., on dashboards or cards) it applies to.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as delete_alert_subscription or delete_card. It does not specify prerequisites (e.g., user permissions, existence of comment) or mention if there are related tools for managing comments.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only states the tool's function without disclosing behavioral traits. It does not indicate side effects (likely none), required permissions, or that it is a read-only operation. The description fails to add context beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the purpose. It is front-loaded and contains no fluff, though it could include more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 required nested parameters, no output schema, no annotations, and many sibling tools, the description is severely incomplete. It omits parameter explanations, output format details, and any usage context. This is insufficient for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description provides no explanation for the required parameters (token, dashcard_id, card_id, export_format). The schema only offers type info and a minimal description on export_format. The description should compensate but does not, making it impossible for an agent to know how to fill these parameters correctly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Export' and the specific resource 'embedded dashcard query', distinguishing it from sibling tools like export_dashcard_query (non-embedded) and run_embed_dashcard_query (run vs export). The purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as run_embed_dashcard_query or export_embed_card_query. There is no mention of prerequisites, context, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only says 'Export' with no details on what the tool returns (file content, URL?), side effects, or authentication requirements. The behavior is under-specified for a public-facing export tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that efficiently states the primary function. However, it could include more essential details without excessive length, but as it stands, it is appropriately sized for a concise definition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the high complexity (nested parameters, 0% schema coverage, no output schema, many siblings), the description is severely incomplete. It omits crucial context such as export format options, response structure, and how to construct the input object.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% as the parameter descriptions are minimal ('Export format' with no valid values). The tool description adds no additional meaning to the parameters, failing to clarify the relationship between uuid and card_id or the allowed export formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Export) and resource (card from a publicly shared document in Metabase). However, it does not differentiate from many similar export siblings like export_public_card_query or export_public_dashcard_query, which also deal with public entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidelines on when to use this tool versus alternatives. No mention of prerequisites (e.g., document must be publicly shared), export formats, or contrasting with other export tools. The description leaves the agent without decision-making context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description provides no behavioral traits beyond the basic retrieval. It does not disclose side effects, permissions, rate limits, or error handling (e.g., what happens if the ID is not found).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise—a single sentence with no wasted words. However, it could be more informative while remaining succinct, such as mentioning the return type or typical use case.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is incomplete. It does not explain what an 'action' is in Metabase, what the output looks like, or any usage context, making it insufficient for an AI agent to use confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal value beyond the input schema. It repeats that the tool retrieves 'by ID', but the schema already describes the 'id' parameter as 'Action ID'. With 0% schema description coverage, the description should compensate, but it fails to elaborate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action is to 'Get an action by ID from Metabase', specifying the verb and resource. However, it does not differentiate from sibling tools like 'get_action_execute_form' or 'list_actions', which cover related but distinct operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description lacks any context for selection among the many 'get_*' tools, such as 'get_action_execute_form' or 'list_actions'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It does not state if the operation is read-only, requires authentication, or any side effects. The parameter 'archived' hints at inclusion of archived timelines, but no further behavioral details given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, which is efficient, but it sacrifices necessary detail. It is front-loaded but lacks information that would make it genuinely helpful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has a nested input object with two parameters and no output schema, the description is insufficiently complete. It does not describe return format, pagination, error conditions, or the specific meaning of 'root collection' in Metabase, which is needed for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no information about the parameters. The input schema has two optional properties ('include' and 'archived') with schema-only descriptions, but the tool description omits any parameter explanation, leaving the agent without guidance on valid values or usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get timelines in the root collection in Metabase' using a specific verb and resource. It distinguishes from siblings like 'get_collection_timelines' (presumably for a specific collection) and 'get_timeline' (individual timeline).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., when to use 'get_collection_timelines' instead). No prerequisites or context about needing the root collection or handling of optional parameters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits, but it only states the action. There is no mention of whether the operation is read-only, any required permissions, rate limits, or data sensitivity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no extraneous words, making it concise. However, it is too brief to be fully informative, and there is no structure that aids scannability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the sibling tools and the lack of an output schema, the description is insufficient. It does not explain what 'query metadata' entails, nor does it differentiate sufficiently from similar dashboard-related tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes an 'id' parameter with a description 'Dashboard ID', but the tool description does not add any additional meaning beyond that. The description fails to compensate for the 0% schema coverage of the outer input object.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb 'Get' and a resource 'dashboard query metadata', which distinguishes it from sibling tools like 'get_dashboard' that likely return full dashboard details. However, 'query metadata' is vague and could encompass multiple things.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives such as 'get_dashboard', 'get_card_metadata', or 'get_dashboard_tile'. The description does not clarify the specific use case or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states 'Get action parameters', which implies a read operation but does not explicitly confirm idempotency, read-only nature, or any side effects. For a tool that likely retrieves data (not destructive), the absence of safety assurances is a gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence. It is concise and front-loaded with the key purpose. However, it could be expanded slightly to include usage context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of an output schema and the presence of nested objects (complex input), the description is insufficient. It does not explain what the returned action parameters contain (e.g., form fields, required values) or how they are structured. The tool is moderately complex, but the description leaves the agent guessing about the response format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has nested properties with descriptions for dashcard_id and dashboard_id, but the top-level 'input' parameter lacks a description. The description adds no extra meaning beyond implying that dashboard and dashcard IDs are needed. With schema description coverage at 0% for top-level parameters, the description should compensate but does not explain the optional 'parameters' field or the role of the nested object.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get action parameters for a dashcard in Metabase' clearly states the verb (Get) and resource (action parameters for a dashcard). While specific, it lacks explicit differentiation from sibling tools like execute_dashcard_action or run_dashcard_query, which are related but distinct operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. For instance, it doesn't mention that this tool is typically used before execute_dashcard_action to retrieve required parameters, or that it's a read-only preparatory step. Sibling tools like get_public_dashcard_execute have different contexts but no comparison is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose whether the tool is read-only, requires specific permissions, or what happens on invalid input. The 'get' prefix implies reading but this is not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and to the point. No unnecessary words, though it could be expanded with essential details without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description does not explain what 'available settings' means, the format of the response, or any example. For a tool returning configuration settings, this is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage per context, the description adds no parameter details beyond the schema's 'Database ID'. The description does not elaborate on the parameter's role or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves available settings for a database connection. It distinguishes from other get_* tools by specifying 'settings' vs general info or metadata, though it doesn't explicitly name siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like get_database or get_database_metadata. The description is minimal and doesn't provide context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must convey behavioral traits. It does not mention that this is a read-only operation, any side effects, authorization requirements, or rate limits. The agent must infer that it is likely non-destructive from the verb 'Get'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no superfluous words. It efficiently communicates the tool's purpose, though it could be expanded with additional useful information without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema, no output schema, and many similar sibling tools, the description is insufficient. It does not explain what a virtual schema is, what the response contains, or how it differs from related tools like get_database_metadata or get_virtual_database_datasets.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the tool description does not elaborate on the parameters. While the input schema itself includes descriptions for id and schema, the tool description adds no additional meaning, failing to compensate for the low coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('virtual schema') for a database in Metabase. It effectively communicates the tool's purpose, though it does not explicitly differentiate from similar sibling tools like get_virtual_database_datasets.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description lacks context about prerequisites, use cases, or when to avoid this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must cover behavioral traits. Only states 'Get details' without describing what details are returned, authentication needs, or any side effects. Lacks disclosure that it's a read-only public access.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single concise sentence with no unnecessary words. Efficient but lacks elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given one parameter, no output schema, no annotations, and many sibling tools, the description is too minimal to fully guide an agent. Missing information on return value and context of use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, and the description adds no extra meaning about the 'uuid' parameter beyond what's in the schema. Does not explain how to obtain the UUID or any constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Get' and resource 'public action in Metabase'. Distinguishes from siblings like 'execute_public_action' or 'list_public_actions' by focusing on retrieving details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives like 'get_action', 'execute_public_action', or 'list_public_actions'. Does not mention prerequisites or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must fully disclose behavior. It only says 'get query results' without specifying output format, pagination, errors, or authentication requirements. For a public tool, it should mention it does not require authentication.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at one sentence, structurally clear, and front-loaded with the action and resource. It earns its place without redundancy, though could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given low complexity (1 param, no output schema, no annotations), the description is too brief. It lacks details on return values, error states, or how the output differs from similar tools like 'get_public_card_query_format'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'uuid' is well-defined in the schema (format, pattern) but the description adds no additional meaning. With 0% schema coverage, the description should compensate by explaining the parameter's role, but it does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get query results for a publicly shared card by UUID from Metabase' clearly states the action (get query results) and the resource (publicly shared card by UUID). It distinguishes from siblings like 'get_public_card' (metadata) and 'get_public_card_tile' (tile), but not from 'get_public_card_query_format' which also gets query results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_public_card' or 'get_public_card_query_format'. There is no mention of prerequisites (card must be publicly shared) or context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It only states what the tool does (get a map tile) but does not disclose return format, whether authentication is needed (though public likely implies none), rate limits, or any side effects. This is insufficient for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, short sentence that is concise and front-loaded. However, it is too brief for the tool's complexity, omitting critical details. It earns a middle score for being to the point but lacking necessary substance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested object, 6 parameters, no output schema, no annotations), the description is incomplete. It does not explain the output (e.g., image URL or binary), parameter roles, or any prerequisites like the need for an existing public dashboard.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 6 parameters with 0% description coverage. The description adds no explanations for any parameter, leaving the agent to guess the meaning of 'zoom', 'x', 'y', etc. Without schema descriptions or clarifying text, the agent cannot correctly select values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the verb 'Get', the resource 'map tile', and the source 'public dashboard dashcard'. It effectively distinguishes itself from sibling tools like get_dashboard_tile (non-public) and get_public_card_tile (for cards, not dashcards).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no context on when not to use it. It is missing any usage recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as read-only nature, authentication requirements, or side effects. For a tool with no annotations, the description should provide more context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but lacks necessary detail. It is front-loaded but too minimal for effective use.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description does not explain return values or behavior. For a tool with three parameters and no annotations, the description is incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has three required properties (uuid, card_id, dashcard_id) but the description adds no explanation of their meaning or usage. With 0% schema description coverage, this is a critical gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The name and description clearly state the tool retrieves query results for a public dashcard in Metabase. It is distinct from sibling tools like 'get_public_card_query' which targets cards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_public_card_query' or other dashcard-related tools. Missing context on prerequisites or scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is minimal and does not disclose any behavioral traits beyond reading revision history. With no annotations provided, it fails to mention aspects like pagination, ordering, or the content of revisions, which are important for agent decision-making.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the core action. It is efficient, though it sacrifices detail for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of an output schema and the need to understand what a revision history consists of, the description is incomplete. It does not explain return format, limits, or how revisions are ordered, which are necessary for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is reported as 0%, meaning the description adds no value over the schema. The schema itself provides a parameter description for 'id', but the tool description does not elaborate on how to use it or any constraints, leaving room for ambiguity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'revision history of a segment from Metabase', making the purpose understandable. However, it does not differentiate this tool from similar ones like get_entity_revision or list_revisions, which reduces clarity slightly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as get_entity_revision or list_revisions. The context signals and sibling list are extensive, but the description offers no usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It only states 'Get valid filter fields' without disclosing if it is read-only, requires authentication, or has side effects. Minimal disclosure beyond the obvious.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the key information. It is appropriately sized with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, but the description does not explain what the return value will be (e.g., list of field IDs or objects). The input has nested objects with a relationship between 'filtered' and 'filtering' that is not clarified. The description feels incomplete for a tool with such parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention the input parameter 'input' or its nested structure. While the schema has descriptions for 'filtered' and 'filtering', the description adds no meaning beyond what the schema already provides. With 0% schema description coverage in the text, the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'valid filter fields' with context 'for dashboard parameters in Metabase'. It is specific enough to distinguish from general field tools like 'get_field', though it does not explicitly differentiate from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. It does not mention conditions, exclusions, or related tools such as 'get_dashboard_param_values' or 'search_field_values'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It only states 'Get', implying a read operation, but does not confirm side effects, permissions, or any behavioral traits. The term 'automagic' is vague and unhelpful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the action and resource, making it efficient. However, it could be restructured to provide more immediate clarity without added length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema with three sub-parameters and no output schema, the description is incomplete. It does not explain what a 'cell' or 'automagic dashboard' means, nor does it describe the return value, making it insufficient for an agent to confidently invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate but fails to add meaning beyond the schema. Parameter descriptions in the schema are minimal (e.g., 'Entity type', 'Cell query'), and the tool description does not clarify what a 'cell' is or how parameters relate to the operation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('x-ray automagic dashboard for a specific cell of an entity in Metabase'), which conveys the basic purpose. However, it does not differentiate from sibling tools like get_xray_entity or get_xray_entity_cell_compare, which are similar in function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. Siblings like get_xray_entity_cell_compare suggest comparison scenarios, but no explicit usage context, prerequisites, or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It does not explain whether the operation is read-only, what the return format is, or any permission requirements. The minimal description fails to provide sufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 8 words, making it extremely concise. It is front-loaded and to the point, but may be under-specified for the tool's context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a listing operation with one parameter and no output schema, the description should indicate what information is returned (e.g., schema names, objects). It does not, making it incomplete for an agent to understand the tool's full behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is one parameter ('id') with a schema description 'Database ID'. However, the tool description adds no semantics beyond the schema; schema coverage is 0% because the description does not mention parameters. Given low coverage, the description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'all schemas in a database', specifying the source 'from Metabase'. It is specific about what it does, but does not differentiate from the sibling tool 'list_database_schemas_with_tables', which may include additional details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'list_database_schemas_with_tables' or 'list_database_tables'. It does not mention any prerequisites, such as needing a database ID, which is already clear from the input schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only implies the tool is read-only by stating 'readable by the current user', but it does not disclose any other behavioral traits like pagination, ordering, or side effects. The description is insufficient for a mutation-free understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately conveys the tool's purpose. There is no redundancy or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and the ambiguous input parameter, the description is incomplete. It does not describe the return format or any additional context needed to use the tool effectively. For a simple list tool, it barely meets minimal completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one required parameter ('input') which is an empty object, and the description provides no explanation of what this parameter does or why it is needed. With 0% schema description coverage, the agent has no insight into how to correctly invoke the tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the verb 'List' and resource 'metrics', and adds the scope 'readable by the current user', which helps distinguish it from other list tools. However, it could be more specific about what constitutes a metric in Metabase, but overall it is clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like list_measures or list_segments. There is no mention of prerequisites or exclusions, leaving the agent without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of behavioral disclosure. It only states it 'lists all documents with public links', but fails to mention key traits such as whether it is read-only, pagination behavior, authentication requirements, or how results are structured. This is insufficient for safe and effective use.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence and very concise, but it is too brief to be effective. It lacks necessary detail, forfeiting completeness for brevity. It earns a middle score because it is not verbose, but it is under-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (no output schema, no annotations, 0% schema description coverage, and many related sibling tools), the description is far from complete. It does not explain what constitutes a 'public link', what the response contains, or any constraints. A more complete description is needed for the agent to use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage via a single parameter 'input' which is an empty object with no description. The tool description adds no information about parameters, their meaning, or how to use them. With 0% schema description coverage, the description must compensate but does not, leaving the user with no understanding of what to pass.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'list' and the resource 'documents with public links', and it distinguishes from the sibling tool 'list_documents' by specifying the subset of documents that have public links. This provides a specific and unambiguous purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives like 'list_documents' or other list tools. No context is provided about prerequisites, scenarios, or exclusions. The description is purely declarative without usage hints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It implies a read-only list operation but does not explicitly state safety, auth requirements, rate limits, or side effects. The minimal description adds little behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It is appropriately sized for a simple list operation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (1 parameter, list operation), the description is incomplete. It lacks details on return format, pagination, or how to use the archived filter. Without annotations or output schema, more context is needed for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the single parameter 'archived'. The schema description 'Filter by archived status' is minimal, and with 0% schema description coverage, the tool description should compensate but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List all pulses in Metabase', specifying the verb 'list' and the resource 'pulses' with scope 'all'. It distinguishes from siblings like list_actions or list_dashboards, but lacks additional detail to differentiate further.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as list_cards or list_alerts. There is no mention of prerequisites, context, or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral traits such as whether the list is paginated, ordered, or includes metadata. With no annotations, the description should provide more context but fails to do so.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded, but it is too concise for a tool with parameters. While there is no wasted text, it sacrifices completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple input schema and no output schema, the description should at least explain the parameters' roles and what is returned. It fails to provide sufficient context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no explanation of the parameters ('include' and 'archived') despite the schema having 0% coverage. It adds no meaning beyond the bare schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List all timelines in Metabase', using a specific verb (list) and resource (timelines). It distinguishes itself from sibling tools like create_timeline, delete_timeline, get_timeline, and update_timeline, which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get_collection_timelines or get_collection_root_timelines. The description lacks context for selecting this tool over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only states the action without disclosing behavioral details such as what moving entails, whether it is reversible, or any required permissions. Since no annotations are present, the description carries the full burden and fails to provide sufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no waste. However, it is too brief to be informative, sacrificing completeness for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and minimal parameter descriptions, the tool definition is incomplete. The agent lacks critical context about the operation's effect and the meaning of parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. The schema parameters are minimally described (e.g., 'Collection ID'), but the description does not clarify what 'id' represents (source or destination) or what 'card_ids' refers to.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Move' and the resource 'dashboard question candidates', and the tool name is specific. However, it does not differentiate from sibling tools like 'move_cards_to_collection' or 'bulk_move_cards'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidelines are provided. The description does not indicate when to use this tool versus alternatives, nor does it specify prerequisites or conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It merely states a notification action without disclosing any behavioral traits like side effects, required permissions, idempotency, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no superfluous words, making it easy to read. However, it may be too brief, sacrificing valuable context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested parameters, no output schema, no annotations), the description is incomplete. It does not explain what the notification entails, return values, or handling of duplicate tables.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the schema. Although the nested schema properties have brief descriptions, the top-level 'input' parameter lacks a description, and the schema coverage is 0%, so the description does not compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Notify' and resource 'Metabase of a new table', making the purpose understandable. However, it does not differentiate this tool from similar sibling tools like notify_database_sync or notify_database_sync_by_name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no context about prerequisites, scenarios, or exclusions, leaving the agent uncertain about tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the behavioral disclosure burden. It fails to mention side effects, safety considerations, or what 'enable persistence' entails operationally. The single sentence is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no unnecessary words. It is appropriately concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having only one parameter and no output schema, the description lacks explanation of persistence, return values, error conditions, or integration context. It is too sparse for an AI agent to fully understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% per context, meaning the description does not explain the 'db_id' parameter. Although the schema itself has a description, the tool description adds no value, violating the requirement to compensate when coverage is low.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Enable persistence') and target ('all models in a database in Metabase'). It is specific and distinguishable from siblings like 'enable_model_persistence' and 'disable_model_persistence', though it does not explicitly differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., 'enable_model_persistence'). No prerequisites, context, or exclusionary conditions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description states admin-only restriction but does not disclose whether the operation is read-only, whether it has side effects, or any rate limits. Lacks behavioral context beyond access control.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is efficient and front-loaded with key actions. Could be restructured to include more critical details without increasing length, but is not verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool is simple (1 param, no output schema), yet description omits expected output format, error handling for invalid tokens, and relationship to preview-related siblings. Insufficient for an agent to fully understand the tool's role.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so description must compensate. It mentions 'by token' but does not add meaning beyond the schema's 'Preview embed token' description. Fails to explain token format, source, or validation behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description specifies verb 'Preview', resource 'embedded card', and method 'by token' plus access restriction 'admin only'. Clearly distinguishes from siblings like 'get_embed_card' which is a retrieval, not preview. However, does not clarify what 'preview' returns (image, data, URL).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives such as 'preview_embed_card_query' or 'get_preview_embed_card_tile'. Only mentions admin access prerequisite but no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It fails to disclose that removal is destructive, irreversible, or requires permissions. The agent has no insight into side effects or safety considerations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that clearly communicates the core action. However, it sacrifices necessary detail for brevity, which slightly reduces its utility.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the destructive nature, two required parameters, no output schema, and no annotations, the description is insufficient. It lacks information on return values, error handling, and version-specific behavior beyond the version note.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no information about the required parameters (dashboard_id, tab_id). The agent cannot infer the correct parameter values or their meaning from the description alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the action ('Remove') and the resource ('a tab from a dashboard'), and includes the Metabase version requirement, which distinguishes it from siblings like add_dashboard_tab or remove_dashboard_card.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives, nor does it mention prerequisites or conditions for use. It simply states the function without usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a mutation but does not disclose potential side effects, authorization requirements, or error conditions. No annotations are present to supplement behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, efficient and front-loaded, but it lacks detail needed for a tool with a nested input schema. It is concise but does not fully earn its place given the missing information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations, no output schema, and a complex nested input, the description barely covers the purpose. It does not explain outcomes, constraints, or the scope (current user) beyond a brief mention.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description only mentions 'providing the new ordering' without explaining the structure of the 'input' parameter or the 'orderings' array. The agent would have to infer all parameter details from the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('reorder') and resource ('bookmarks') for the current user. It distinguishes from siblings like create_bookmark, delete_bookmark, and list_bookmarks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as create_bookmark or list_bookmarks. There is no mention of prerequisites (e.g., existing bookmarks) or scenarios where reordering is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits but only states the action. It does not explain what rescanning entails (e.g., triggers a sync, overwrites cached values, potential side effects on queries, or required permissions). This is insufficient for an AI agent to understand the impact.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, which is efficient but arguably too brief. It contains no redundant words, fitting within the 10% weight for conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, and the presence of ambiguous sibling tools, the description is incomplete. It does not specify return values, confirmation of completion, or how the tool fits into the workflow, leaving the agent uncertain about the tool's full role.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter (id) with description 'Table ID', and the tool description adds no further semantics. Since schema description coverage is 0%, the description should compensate by explaining how to obtain the ID or what the parameter represents, but it does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool rescans field values for a table in Metabase. The verb 'rescan' is specific and contrasts with sibling tools like 'rescan_database_values' and 'rescan_field_values' at different granularity levels. However, it does not explicitly distinguish itself from 'rescan_field_values', which operates on individual fields, so clarity is slightly diminished.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'rescan_database_values' or 'rescan_field_values'. There is no mention of prerequisites, context, or situations where this tool should be avoided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for disclosing behavioral traits. It fails to mention that the operation is likely destructive (overwrites current dashboard state), requires permissions, or that it may be irreversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it is under-specified. It is not efficiently informative; it could be longer without becoming wordy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is insufficient. It does not explain what happens after reverting (e.g., dashboard state changes, previous revision may be lost), nor does it provide any usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has two required parameters, but the description does not describe them or their roles. Since schema description coverage is 0%, the description adds zero value beyond the schema, leaving the agent with no understanding of how to use them.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Revert'), the resource ('a dashboard'), and the target state ('to a previous revision'). It is specific and distinguishes from siblings like 'revert_revision' which is more general.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives like 'list_dashboard_revisions' or 'get_entity_revision'. There is no mention of prerequisites or context such as needing a known revision_id.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits (e.g., side effects, permissions, idempotency). It only states a write operation without detailing any consequences, prerequisites, or limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no extraneous information. It is well-structured and front-loaded, but its brevity sacrifices necessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, annotations, and detailed parameters, the description is insufficient. It does not address return values, error handling, or prerequisites, which are critical for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides basic descriptions for 'dashboard' and 'parent_collection_id', but the tool description adds no additional context. Parameter semantics are minimal, leaving ambiguity about the structure and constraints of the 'dashboard' object.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('save'), resource ('dashboard'), and destination ('specific collection'). It effectively communicates the primary purpose, though it does not explicitly distinguish from sibling tools like 'save_dashboard' or 'move_cards_to_collection'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not indicate scenarios where this tool is appropriate or inappropriate, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral traits beyond the basic action. It does not mention if the sync is asynchronous, destructive, or has side effects. With no annotations provided, the description fails to convey expected behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise, but it lacks any structure or detail. It is adequate but could be expanded without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a single parameter, but no output schema and no annotations. The description is too minimal to be complete. It does not explain what happens after triggering or what response to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the schema. With 0% schema description coverage (as per context), and no parameter details in the description, the agent gets no help understanding how to use the 'id' parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Trigger a sync') and the resource ('a database in Metabase'), with a specific verb and resource. It distinguishes from siblings like 'sync_database_schema' and 'sync_table_schema' by implying a full database sync.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or context. The agent is left without direction on when 'trigger a sync' is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It only says 'Undo a global unsubscribe' without mentioning effects, idempotency, authorization needs, or what happens on success/failure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a single sentence that is front-loaded. However, it may be too brief for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested parameter, lack of output schema, and absence of annotations, the description is incomplete. It does not explain the relationship to sibling tools like unsubscribe_notification_global, nor the expected result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite the input schema having property descriptions, the context signals indicate 0% schema description coverage. The tool description adds no additional meaning to the parameters (email, hash) beyond what the JSON schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it undoes a global unsubscribe for an email in Metabase. It uses a specific verb and resource, and can be distinguished from siblings like undo_pulse_unsubscribe which is for pulses.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as undo_pulse_unsubscribe or unsubscribe_notification_global. The context signals indicate many related tools, but the description lacks usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description only states the action without disclosing side effects, authentication needs, or reversibility. Minimal behavioral context beyond the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with action, no wasted words. Efficient but could include more context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested object input and three required parameters, the description is too minimal. It doesn't explain what a pulse is, what the hash represents, or what happens after unsubscribing. Incomplete for the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has basic property descriptions (e.g., 'Unsubscribe hash', 'Email address to unsubscribe', 'Pulse ID'), but the description adds no extra meaning. Schema coverage is 0% (descriptions are minimal), so description should compensate but doesn't.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (unsubscribe) and resource (pulse email notifications) with a specific verb, but does not differentiate from siblings like unsubscribe_pulse or unsubscribe_notification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., unsubscribe_pulse, unsubscribe_notification). No when-to-use or when-not-to-use information provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states 'Update' without indicating whether the operation replaces permissions, requires a correct revision, or has destructive consequences. The agent is uninformed about potential conflicts or authorization needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (single sentence), which is efficient but omits critical details. It is front-loaded, but the trade-off reduces utility. Every sentence earns its place, but the overall brevity hurts comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input schema (nested permissions graph) and the presence of sibling tools for reading or manipulating permissions, the description is inadequate. It does not explain the return value (no output schema) nor the relationship to other tools, leaving gaps for agent selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage for the top-level parameter ('input'), the tool description adds no additional meaning. The nested schema fields have some descriptions, but the tool description itself does not explain the parameters, revision number, or permission structure. This fails to compensate for the schema's coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Update the data permissions graph for groups and databases in Metabase' clearly states the action (update), the resource (data permissions graph), and the scope (groups and databases). It is specific and distinct from sibling tools like get_data_permissions or update_permission_group.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., update_permission_group). It lacks prerequisites, side effects, or context for invocation, leaving the agent without decision-making support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates the tool is a mutating operation but does not disclose side effects, permission requirements, or reversibility. With no annotations, the description should provide more behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that captures the essence. It is well-structured and front-loaded, but could arguably include more detail without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with a complex nested input schema and no output schema, the description is insufficient. It does not explain how to use the input object or what the response contains. The tool's complexity demands a richer description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description lists some parameters (display name, description, etc.) but the schema has many more not mentioned (e.g., settings, coercion_strategy, fk_target_field_id). The nested structure of the 'input' parameter is not explained. Schema coverage is 0%, so the description should compensate but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool updates field metadata and lists specific attributes (display name, description, semantic type, visibility settings). This provides a good understanding of the tool's purpose, though it does not differentiate it from sibling tools like 'update_field_values'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no prerequisites or limitations mentioned. The user is left to infer usage from the description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral traits such as required permissions, side effects (e.g., whether duplicate memberships are allowed), or error handling. With no annotations provided, the description carries the full burden but falls short.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks structure. It is front-loaded, yet it omits important details, making it insufficient for a well-rounded understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is inadequate. It does not explain the return value, success criteria, or any constraints, leaving significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for 'user_id' and 'group_id', which already convey meaning. The tool description adds no further explanation beyond what the schema provides, achieving the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (add a user to a permission group) and the context (Metabase). It effectively distinguishes from siblings like 'delete_membership' or 'clear_memberships', but does not differentiate from 'create_permission_group'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'update_membership' or 'clear_memberships'. There is no context about prerequisites or scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the full burden of behavioral disclosure. It only says 'Copy', failing to mention side effects like whether cards, tabs, or permissions are copied, or if the original is affected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It is concise and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (copying a dashboard involves multiple sub-objects), the description is too minimal. It does not clarify return value or behavior, and with no output schema, the agent lacks essential context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the tool description does not explain any parameters. Although the schema itself includes parameter descriptions, the tool description fails to add value or clarify parameter usage, which is required when coverage is low.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the verb 'Copy' and the resource 'existing dashboard in Metabase', making the action clear. It distinguishes from sibling copy tools like copy_card and copy_document, but lacks detail on what is included in the copy.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like create_dashboard or copy_card. Prerequisites, such as needing write permissions or the dashboard existing, are omitted.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It only states the basic action (creating a comment) but does not disclose permissions, side effects, rate limits, or whether the operation is reversible. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. However, it may be overly terse, sacrificing important details for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description should explain more about the 'model' context (e.g., what types of models are supported) and what 'creating a comment' entails. It leaves ambiguity about the resource and does not cover return values or side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the description must compensate for parameter clarity, but it does not mention any parameters. The input schema has its own descriptions, but the description adds no meaning beyond 'Create a new comment'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create a new comment on a Metabase model' uses a specific verb (Create) and resource (comment on a model), clearly distinguishing it from sibling tools like add_comment_reaction (adds reaction) and update_comment (updates existing comment).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. It does not mention prerequisites, context, or scenarios where other tools (e.g., update_comment, add_comment_reaction) would be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states 'Create' with no detail on side effects, permissions, destructure hints, or error conditions. For a creation tool, more transparency is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no redundancy. It is front-loaded with the most important idea. However, it could include additional key details without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a complex nested input schema with multiple required fields and no output schema. The description is far too brief to cover the necessary context for correct usage. It lacks information on return values, error handling, and behavior of the subscription creation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention any parameters. Schema coverage is 0%, so the description should compensate, but it adds zero value beyond what's in the schema. The nested input object has multiple required fields like dashboard_id and channels, none described in the tool description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create'), the resource ('dashboard subscription'), and specifies the type ('email/Slack notification'). It distinguishes this tool from siblings like 'list_dashboard_subscriptions' and 'update_dashboard_subscription', and from 'create_pulse' by specifying the subscription type. The verb+resource is clear and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no prerequisites, no when-not-to-use conditions. Given siblings like 'create_pulse' and 'update_dashboard_subscription', explicit context is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It only states 'Create a new document', implying a write operation, but omits details like idempotency, side effects, required permissions, or error behavior. This is insufficient for an agent to understand the implications of using the tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, highly concise. However, given the nested parameter structure and lack of annotations, it may be too terse, sacrificing necessary detail. The front-loading is good (verb+object first), but the extreme brevity undermines completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and a nested input parameter with 0% schema coverage, the description is incomplete. It does not explain return values, required permissions, or how to properly construct the input object. The agent lacks critical context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description adds no information about the input parameter or its sub-fields (name, content, collection_id). It does not clarify their meaning or usage, leaving the agent reliant solely on the schema, which lacks descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create a new document in Metabase' clearly specifies the verb (Create) and the resource (document), distinguishing it from sibling tools like create_card or create_dashboard. It unambiguously indicates this tool's role in creating a specific entity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives or any preconditions. It fails to mention context such as required permissions, whether the user must have a parent collection, or how creation differs from other creation tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description fails to disclose behavioral traits such as whether the tool is idempotent, what happens if the sample database already exists, or any side effects. A mutation tool with no behavioral context is severely lacking.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, zero waste. The information is front-loaded and directly states the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter create tool, the description is minimal but lacks details on what the tool returns (no output schema) and potential implications (e.g., if already exists). It is marginally adequate but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema covers all inputs. The description does not need to explain any parameters. Baseline 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and the specific resource ('the built-in sample database in Metabase'). It distinguishes from generic 'create_database' by specifying 'built-in sample'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., 'create_database'). Does not mention prerequisites, idempotency, or that it's typically used once for setup.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a destructive action but does not explicitly state that the deletion is irreversible, require permissions, or affect associated data. With no annotations provided, the description carries the full burden of behavioral disclosure, yet it adds no traits beyond the operation name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at 5 words, front-loaded with the key action and resource. Every word serves a purpose with no unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool, the description lacks completeness. It does not mention the permanent nature of the deletion, required permissions, or any side effects. Given the lack of annotations and output schema, more context would be beneficial for safe usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not mention any parameters, and the schema description coverage is 0% (per context), meaning the description should compensate. Although the schema includes a description for 'id', the tool description adds no meaning beyond the schema, failing to enhance understanding of the input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Delete' and the resource 'action from Metabase', making the purpose immediately understandable. It distinguishes itself from sibling tools like create_action and update_action by specifying the delete operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool over alternatives, such as delete_action_public_link or other delete tools. There are no prerequisites, context, or exclusions mentioned, leaving the agent without decision-making support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must stand alone. It indicates 'deactivate' rather than permanent deletion, but omits details about reversibility, side effects on user data, or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the action. It contains no unnecessary words or repetitions.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is incomplete. It does not explain what the tool returns, how to handle failures (e.g., deleting the last admin), or the state of the user after deactivation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the 'id' parameter beyond what the input schema provides (e.g., 'User ID'). With 0% schema description coverage, the tool description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Delete (deactivate)' and the resource 'user' within 'Metabase'. It distinguishes from sibling tools like 'reactivate_user' by implying deactivation, but could be more explicit about the action's nuance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'update_user' or 'reactivate_user'. The description does not mention prerequisites or contexts where deactivation is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description merely states action without detailing side effects, permissions, or reversibility. For a destructive operation, more transparency is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely short (one sentence), but lacks essential details for a tool with no annotations and no output schema. Under-specification outweighs brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and 0% schema coverage, the description fails to provide sufficient context. Missing when to use, what happens after discarding, and relation to sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but description adds no meaning beyond 'field'. The 'id' parameter is explained only in schema as 'Field ID'; description does not clarify what the ID represents or how to obtain it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'discard' and resource 'cached values for a field', distinguishing it from siblings like 'discard_database_values' and 'discard_table_values'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like 'rescan_field_values' or 'get_field_values'. Missing context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states the action without revealing side effects, required permissions, or whether it is a UI-only dismissal or a server-side action. This minimal disclosure is insufficient for a mutation-like tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that directly states the tool's function. It avoids unnecessary words but may be overly terse. It is front-loaded and easy to parse, though it could benefit from additional structuring.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no annotations, no output schema), the description provides the core purpose. However, it lacks usage guidelines and parameter context, making it minimally adequate but not comprehensive for an AI agent to use confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema contains a single parameter 'id' described as 'Database ID'. The tool description does not reference this parameter or explain how to use it, adding no value beyond the schema. Although the schema provides a basic description, the tool text fails to connect the parameter to the action.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'dismiss' and resource 'loading spinner for a database', making the tool's purpose unambiguous. It distinguishes itself from the sibling 'dismiss_user_modal' which targets a different UI element. However, it does not elaborate on the broader context or implications of the action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool, prerequisites, or alternatives. The description lacks context about the circumstances that warrant dismissing the spinner, leaving the AI agent to infer usage without clear direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only states it returns mentions for the current user, but does not indicate if it's read-only, required permissions, or the format of results. The minimal transparency could mislead about behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is concise and to the point. However, it may be too brief given the lack of detail in other dimensions. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no effective parameters, no output schema), the description is minimally adequate. It lacks behavioral details but covers the basic purpose. Could be improved with output format or usage hints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one required parameter 'input' which is an empty object. The description adds no meaning about what this parameter is for, and schema description coverage is 0%. The tool effectively takes no parameters, but this is unclear.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get) and resource (comment mentions) with a scope (for the current user). It distinguishes from siblings like list_comments, though it's somewhat vague on what exactly constitutes a 'mention'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like list_comments or other get_* tools. The description does not mention context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries all behavioral disclosure. It minimally states it 'gets' a tile but does not describe side effects, permissions, or whether it returns an image. The description is too brief to adequately inform the agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, no unnecessary words, and front-loaded with the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with multiple coordinate parameters and no output schema, the description lacks crucial details such as return type (image?), coordinate system, and required context (e.g., dashboard_id must refer to an existing dashboard). This leaves the agent with insufficient information to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite the input schema having descriptions for each nested property, the context indicates 0% schema coverage, meaning those descriptions are not counted. The tool description adds no insight into parameters; it only mentions 'dashboard card'. The description fails to explain the meaning or usage of zoom, x, y coordinates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get) and resource (a map tile for a dashboard card in Metabase). However, it does not differentiate from sibling tools like get_card_tile or get_embed_dashboard_tile, which also retrieve tiles but in different contexts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. With many similar tile-getting siblings (get_card_tile, get_public_dashboard_tile, etc.), explicit usage context is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It does not disclose read-only nature, error handling, or whether schema list is complete. Only restates the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is efficient but too brief to cover essential information. Front-loads purpose but lacks details, making it less helpful for agent decision-making.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no description of return value structure. Tool returns syncable schemas but does not explain what that means or how to interpret response. For a simple tool with one param, still incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter 'id' described in schema as 'Database ID'. Description does not add extra meaning, but schema already provides sufficient info. Baseline 3 for high coverage singularity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get' and resource 'syncable schemas for a database in Metabase'. It distinguishes from siblings like 'get_database_schemas' by specifying 'syncable', but does not explicitly differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'get_database_schemas' or 'list_database_schemas'. No context on prerequisites or typical scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It does not mention whether the operation has side effects, authentication requirements beyond the token parameter, rate limits, or error states. It only describes the basic action without safety context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded with the key action. However, it could be slightly more structured but remains effective with minimal waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of nested parameters and no annotations or output schema, the description is incomplete. It does not explain the return value format, potential errors, token usage details, or how the dashcard results are structured.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add any additional meaning to the parameters beyond what is in the input schema. Although the schema has descriptions for 'token', 'dashcard_id', and 'card_id', the context signal indicates 0% schema description coverage, meaning the description should compensate but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get card results for a dashcard in an embedded dashboard from Metabase', specifying the verb 'Get' and the resource 'card results for a dashcard', which distinguishes it from siblings like 'get_embed_card_query' or 'get_embed_dashboard_tile'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'get_embed_dashboard_tile' or 'get_embed_dashboard_params'. There are no exclusions or contexts mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits like read-only nature, required permissions, or response format. This is a significant gap for a tool fetching history.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no superfluous words. It front-loads the verb and resource. However, it could benefit from slightly more detail without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and minimal annotations, the description is adequate for a basic tool. However, it omits context about the return format and how this tool relates to similar ones like 'list_revisions'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no new meaning beyond the input schema, which already includes parameter descriptions for 'id' and 'entity'. It does not elaborate on valid entity types or value constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves revision history for a specific entity, specifying the parameters type and ID. However, it does not differentiate from siblings like 'list_revisions' or 'get_segment_revisions'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides basic usage (get revision history for a specific entity) but lacks explicit guidance on when to use this tool over alternatives. No exclusions or context for when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose whether the tool has side effects, requires permissions, or is read-only. For a data retrieval tool, this lack of transparency is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it lacks necessary context. It barely earns its place as it only repeats the tool name. A slightly longer description with usage guidance would be more effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no mention of return format, the description is incomplete. Given that the tool has nested parameters and is a getter, more context about the response structure is expected.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for the nested parameters 'id' and 'remapped_id', so the schema already conveys meaning. The tool description adds no additional parameter information. Despite the context signal indicating 0% schema coverage, the actual schema descriptions exist, earning a baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'remapping between two fields', which distinguishes it from sibling tools like 'get_field' or 'get_field_related'. However, it could be more specific about what 'remapping' means.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. It is implicitly a read operation, but there is no mention of prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It only states the action without mentioning any side effects, error conditions, or limitations. The tool appears to be a read operation, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no superfluous words. It is optimally concise for the information provided.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested object parameter, many siblings, no output schema, no annotations), the description is insufficient. It omits the return format, the meaning of 'remapping', and how it differs from similar tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, and the tool description does not explain what 'token' or 'param_key' represent. The description adds minimal context by mentioning 'parameter of a preview embedded dashboard', but the parameters remain ambiguous.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets a remapping for a parameter of a preview embedded dashboard. It specifies the verb ('get') and the resource ('remapping'), but does not differentiate from siblings like 'get_embed_dashboard_param_remapping' or 'get_preview_embed_card_param_remapping'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. There are many param remapping tools, and the description does not mention prerequisites, context, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the full burden. It does not disclose any behavioral traits beyond being a retrieval, such as whether it is read-only or what side effects occur. A simple 'get' implies safety but is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded and concise. However, it is under-specified and could include more context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and detailed parameter info, the description is incomplete. It does not describe the return format, error cases, or how this tool relates to other dashboard tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (no descriptions for properties). The description adds no meaning beyond the parameter names ('uuid', 'param_key'). It fails to explain what 'remapping' means or the format/constraints of these parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific verb 'Get' and the resource 'remapping for a parameter of a public dashboard'. This distinguishes it from sibling tools like 'get_public_dashboard_params' or 'get_public_dashboard_param_values'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. There is no mention of prerequisites (e.g., needing the dashboard UUID) or context about when remapping is relevant.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior, but it only states what items are returned. It does not mention that pagination (limit/offset) and filtering (models) are supported, nor does it clarify whether subcollection items are included or if the response structure is simplified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, one sentence with no wasted words, and the verb+resource is front-loaded. While brevity is good, it misses important details, so it earns a high but not perfect score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has three modifiable parameters, no output schema, and no annotations, the description should explain pagination and filtering capabilities. It fails to do so, leaving the agent with incomplete information for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description adds no information about the three parameters (limit, models, offset). It does not explain their purpose, defaults, or how they control output, leaving agents to rely solely on the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'items within the root collection in Metabase', specifying the scope (root) which differentiates it from sibling tools like 'get_collection_items' that target specific collections. It also mentions item types (cards, dashboards, etc.), adding clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any when-to-use or when-not-to-use guidance. It omits alternatives like 'get_collection_items' for non-root collections, leaving the agent to infer usage from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the output is a PNG but does not confirm read-only behavior, authentication requirements, rate limits, or whether the tile is dynamically generated. The lack of annotation coverage makes this a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence. It is concise but lacks structure, such as separating the core action from the optional filter. It could benefit from explicit mention of the required coordinates and optional filter in a more readable format.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a nested object schema (x, y, zoom, card_id), no output schema, and numerous sibling tile tools, the description is insufficient. It does not explain the coordinate system or how to determine zoom, x, y values, nor does it describe the tile size or response format (e.g., direct PNG bytes vs. URL).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all parameters ('Tile X coordinate', etc.), giving 100% coverage. The description only reiterates the optional card_id filter without adding new meaning beyond the schema. Baseline 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a map tile PNG for table data, with optional card ID filtering. It uses a specific verb-resource pair ('Get a map tile PNG') and distinguishes the data source ('table data') but does not differentiate from the sibling 'get_card_map_tile', which likely serves a similar purpose for card-specific tiles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lacks any guidance on when to use this tool versus alternatives like 'get_card_map_tile' or other tile retrieval tools. It mentions an optional filter but provides no context on prerequisites, coordinate system conventions, or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for disclosing behavioral traits. It only states that the tool initiates a migration, but does not reveal whether the operation is synchronous or asynchronous, what permissions are needed, what happens to existing migrations, or what the response contains. The agent gains no insight into side effects or execution behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is direct and to the point. It contains no extraneous words or information. For a simple tool with one parameter, this level of conciseness is appropriate and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and any additional context, the description is far from complete. It does not explain what happens after initiation (e.g., returns a migration ID, starts an async process), what the expected outcomes are, or how to monitor progress. For a potentially impactful operation like a cloud migration, this is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not add any parameter information beyond the schema. While the schema itself includes a description for store_api_key ('Metabase Store API key used to authenticate the migration'), the tool description ignores parameters entirely. For a tool with only one parameter, the description should at least reference the purpose of the API key or its role. The 0% schema description coverage further emphasizes the lack of parameter guidance in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Initiate') and the resource ('cloud migration to Metabase Cloud'). The verb and noun combination is specific, and the sibling names (cancel_cloud_migration, get_cloud_migration) make it distinct from related tools. However, it does not explicitly exclude other actions like checking status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., cancel_cloud_migration, get_cloud_migration). There is no mention of prerequisites, such as whether a migration must not already be in progress, or what conditions are required to initiate a migration. This leaves the agent without context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the tool lists all segments, but does not disclose key behavioral traits such as whether it is read-only, whether pagination is involved, what 'all' means (e.g., across workspaces?), or any rate limits. This is insufficient for an agent to understand side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence) and front-loaded, which is good for conciseness. However, it sacrifices important information that an agent needs, making it too minimal. Every sentence should earn its place, but this single sentence is insufficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description leaves significant gaps. It does not explain the structure of the returned list, whether there is any filtering or sorting, or how to handle potential errors or empty results. For a tool that presumably returns a list of segments, more context is needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one required parameter 'input' which is an empty object with a non-descriptive description 'Parameters for listing segments'. Since the parameter appears to be a dummy placeholder with no meaningful properties, the description should clarify that no arguments are needed or what the empty object signifies. The schema coverage is 100% but fails to add value. The score is baseline 3 as the parameter is essentially meaningless.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns a list of all segments in Metabase, specifying the verb 'Get list' and the resource 'segments'. However, it does not differentiate from other list tools such as list_all_tables or get_segment (which retrieves a single segment), but the purpose is clear enough.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like search, list_segments (if it exists), or get_segment for a specific segment. There is no mention of prerequisites or context, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a mutation operation ('move') but does not disclose any side effects, required permissions, or whether the operation is reversible. No annotations are provided to compensate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It efficiently conveys the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema and no annotations, the description is too minimal. It lacks details about the return value, error conditions, or behavioral nuances needed for safe agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention the parameters at all. Although the input schema documents 'card_ids' and 'collection_id', the description adds no additional meaning or context about their usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (move) and the resource (multiple cards) and the target (a collection). It is specific and matches the function name, but it does not differentiate from similar sibling tools like 'bulk_move_cards' or 'move_collection_dashboard_question_candidates'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., 'bulk_move_cards' might also move cards). There is no mention of prerequisites, limitations, or recommended contexts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states the action with no behavioral details (e.g., permanence, permission requirements, side effects). The version note is helpful but insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that is concise, front-loaded, and efficient. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple removal tool with no output schema and no annotations, the description is minimally adequate but lacks information on return values, side effects, or error conditions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is reported as 0%, and the tool description adds no meaning beyond the parameter names. The description repeats the concept but does not explain the parameters' roles or constraints beyond the schema fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action ('Remove') and the object ('a card from a dashboard'), with a version constraint. It distinguishes from sibling tools like 'remove_dashboard_tab' and 'add_dashboard_card', though without explicit differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'add_dashboard_card', 'delete_dashboard', or 'remove_dashboard_tab'. Missing prerequisites, context, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behavior. It implies a read operation but lacks details on authentication requirements, rate limits, error handling, or what happens if the card is not found.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Efficiently conveys the basic purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested object with three required parameters and no output schema, the description is too brief. It does not cover input validation, error cases, or return format, leaving significant gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate. It mentions 'parameter of a public card' and 'search' but does not explain the 'uuid' or 'param_key' fields, nor the nested input structure. Missing context for the query parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (search), resource (values for a parameter of a public card), and context (Metabase). It distinguishes from some siblings by specifying 'public card', but could better differentiate from similar tools like 'get_public_card_param_values'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'get_public_card_param_values' or 'search_card_param_values'). No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states only that it syncs schema, but fails to disclose important behaviors like whether it is destructive, requires specific permissions, or has any side effects on data. The description is insufficient for an agent to understand the tool's behavioral impact.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and to the point, but it is too brief to be fully informative. It earns its place but lacks detail that could be added without verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (sync operation, single parameter, no output schema, no annotations), the description is incomplete. It omits information about return values, prerequisites, and what happens during sync. An agent would need additional context to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (the schema only says 'Database ID' for the id field). The tool description adds no additional information about the parameter beyond what the schema provides. For a low-coverage schema, the description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (sync) and specific resource (database schema) and distinguishes from a full resync, making the purpose clear. However, it does not elaborate on what 'sync schema' means operationally.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'schema only, not a full resync' implies when to use this tool over a full resync, but it does not explicitly mention alternatives like sync_database or sync_table_schema. Usage context is implied but not fully spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are available, so the description bears full responsibility for behavioral disclosure. It only states 'Update an existing action' without detailing side effects, permission requirements, or what happens when updating specific fields like 'archived' or 'template'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no redundancy. However, it could be slightly more informative without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input schema (nested object with many optional fields), the lack of annotations, and no output schema, the description is inadequate. It does not explain update behavior, partial updates, or field constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention any parameters. With 0% schema description coverage, the description must compensate, but it fails to add any value beyond the schema's own property descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'existing action' in Metabase. It distinguishes from sibling tools like create_action, delete_action, and get_action by specifying the update operation on an existing resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_action or delete_action). There is no mention of prerequisites, such as needing an existing action ID, although the schema requires it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only says 'Update' which implies mutation, but does not disclose side effects (e.g., does it enable/disable Google SSO?), required permissions, validation behavior, or consequences. For a mutation tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is front-loaded with the action and resource, and every word earns its place. This is ideal for an AI agent scanning tool descriptions.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a mutation with no output schema and no annotations, the description is too brief. It does not explain what happens after the update (e.g., confirmation, errors), what the response looks like, or any prerequisites. A more complete description would include at least the return value or side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% meaning the tool description does not explain parameters. Although the JSON schema properties have descriptions, the tool description adds no additional meaning or usage guidance for the parameters. The agent must rely solely on the schema, which is adequate but the description does not compensate for the lack of direct parameter explanation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Update Google authentication settings in Metabase' clearly states the action (update) and resource (Google authentication settings) with context. It distinguishes from sibling tools like update_ldap_settings or update_slack_settings, but could be more specific about which settings are updated (though the schema covers that).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool over alternatives, such as update_setting or configure_email. It does not mention prerequisites, dependencies, or typical use cases. This leaves the agent without context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It only states the basic operation without describing side effects (e.g., whether the update is atomic, what fields are allowed to be updated together, or if the tool requires specific permissions). No mention of return value or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it lacks any structural elements or additional context that could enhance understandability. It is minimal but not overly verbose, earning a middle score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the nested input schema and the lack of an output schema or annotations, the description is insufficient. It does not explain what the response looks like, what fields cannot be updated, or any dependencies like timeline_id requirement. The description is too brief for a tool that modifies data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already contains detailed descriptions for each parameter (e.g., id, icon, name, archived, etc.), so the tool description does not add additional semantic meaning. However, the schema coverage is actually high despite the context signal indicating 0%, so the baseline is appropriate. The description does not elaborate on parameter relationships or constraints beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Update an existing timeline event in Metabase' which indicates the action (update) and the resource (timeline event). It is concise and unambiguous, though it does not explicitly differentiate from sibling tools like create or get, but the verb 'update' inherently distinguishes it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like create_timeline_event or get_timeline_event. There is no mention of prerequisites, typical use cases, or scenarios where a different sibling tool would be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behavior. It states append and existing table, but does not mention required permissions, error handling (e.g., if table doesn't exist), or whether duplicates are handled. Minimal behavioral detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise but too brief. It front-loads the purpose but omits necessary details. Acceptable for simplicity but not optimal for completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description leaves gaps: it doesn't specify that a CSV must be uploaded beforehand, the outcome on success, or any side effects. Incomplete for a mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter (table_id) with 0% schema description coverage. The description does not elaborate on how to obtain the table_id or any additional constraints. For a single-param tool, more semantic guidance is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Append rows from CSV upload), the target (existing table in a database), and the context (Metabase). It distinguishes from sibling tools like upload_csv or replace_table_csv.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., replace_table_csv). No prerequisites mentioned, such as the need for a prior CSV upload or table existence. The description lacks context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It states 'clear' implies a destructive action, but it does not disclose whether it disables email, requires authentication, or is reversible. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence) but under-specified. It lacks context that would be useful for an AI agent, such as effects and usage. It is not overly verbose but could be improved with more detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a clear operation with no output schema and no annotations, the description is incomplete. It does not explain the consequences, such as whether email functionality stops working or the configuration reverts to defaults. This is inadequate for a destructive tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters (0 params), so schema coverage is 100%. According to the guidelines, baseline is 4 when there are no parameters. The description does not need to add parameter info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Clear') and the resource ('the SMTP email configuration in Metabase'). It distinguishes from siblings like 'configure_email' (which sets up) and 'test_email'. However, it could be more specific about what 'clear' means (e.g., reset to default, delete settings).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool vs alternatives. For instance, it does not mention that this should be used to disable email or revert to default, nor does it contrast with 'configure_email' or 'update_setting'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral traits beyond the fact that it creates an action. With no annotations provided, the description carries full burden yet fails to mention mutation behavior, persistence, side effects, or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no unnecessary words. It is concise and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input object and lack of output schema, the description is too brief. It does not explain the meaning of action types, expected response, or how to interpret parameters beyond the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for each property (e.g., 'Action display name', 'Type of action'), so the description adds no new parameter information. Coverage is effectively high, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'create' and the resource 'action', with the context 'in Metabase'. It distinguishes from siblings like 'create_action_public_link' and 'update_action', but does not elaborate on what an action entails in Metabase.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. There is no indication of when to use this tool versus alternatives like 'update_action' or other 'create_*' tools. Prerequisites or conditions are not mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose side effects, permissions needed, or what happens after creation (e.g., immediate visibility). Only states the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise and front-loaded. However, it sacrifices necessary detail for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and the complex nested input parameter, the description is insufficient. It doesn't explain the required fields (name, display, dataset_query) or provide examples, leaving the agent without critical context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (none of the inner properties have descriptions in the schema? Actually they do, but the coverage metric says 0% - meaning the description field of the schema is not filled? The schema shows descriptions for some properties, but the context says 'Schema description coverage: 0%'. So the descriptions in the schema are presumably not counted. The tool description adds no parameter-level information beyond what's in the schema, and with low coverage, more is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (create) and resource (card/saved question) and specifies the context (Metabase), distinguishing it from sibling tools like update_card or copy_card.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., create_dashboard_card for adding to a dashboard). No mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only states the output (UUID) but fails to disclose the side effect of making the dashboard publicly accessible, whether the link is permanent, any destruction, or authentication requirements. This is a significant gap for a tool with potential impact.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It could be improved by adding a bit more context without becoming verbose, but it is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is too brief. It does not explain the implications of creating a public link, the format of the return value (e.g., is it a URL, just the UUID?), or any limits. A tool that creates public access requires more completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although the input schema includes a description for dashboard_id, the context indicates 0% schema description coverage (likely due to the outer input object lacking description). The tool description adds no extra meaning beyond the schema and does not explain how to find or use the dashboard ID.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create'), the resource ('public sharing link for a dashboard'), and the return value ('returns UUID'). It distinguishes from sibling tools like create_card_public_link by specifying 'dashboard'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., other create public link tools, or sharing via other means). There is no mention of prerequisites, permissions, or context where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only mentions creation, omitting behavioral details like side effects, access permissions, or reversibility. For a mutation, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but overly brief. Lacks necessary details without becoming verbose, resulting in a trade-off between conciseness and completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations or output schema, the description fails to specify link format, sharing behavior, or post-creation steps. Incomplete for an action that creates a resource.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description adds no meaning beyond 'Document ID'. The nested input object is not explained, assuming familiarity with the structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Create' and the specific resource 'public link for a document', distinguishing it from sibling tools like create_card_public_link or create_dashboard_public_link.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as create_card_public_link or create_dashboard_public_link. The description lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states the basic creation action, omitting any details about side effects, permissions, idempotency, or error scenarios. This is insufficient for a tool without annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the core purpose. It is front-loaded and contains no unnecessary words or information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, missing output schema, and a nested object parameter, the description should provide more context about the return value, side effects, or structural hints. It only states the basic action, which is inadequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all four parameters (name, synonyms, definition, collection_id), so the tool description adds no additional meaning. The schema coverage is effectively 100%, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and the resource ('glossary entry'), and differentiates from sibling tools like update_glossary_entry and delete_glossary_entry. However, it does not define what a glossary entry is, leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as update_glossary_entry or list_glossary. The description lacks any context about intended use cases, prerequisites, or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description only says 'create' without disclosing side effects, permissions required, or what happens after creation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested parameter, many siblings, and no output schema, the description is severely lacking. It does not explain what a measure is, how to structure the definition, or what the response looks like.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Description adds no meaning beyond the schema's brief property descriptions ('Measure name', 'Measure definition'). The 'definition' parameter remains unexplained as an arbitrary object.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (create) and resource (measure) within Metabase, distinguishing it from update_measure and other create_* tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like create_metric or create_card, nor any prerequisites or context for creating a measure.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behaviors. It indicates soft-deletion but does not explain what this entails (e.g., moving to trash, reversibility, side effects, or consequences for collection contents).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and to the point, no wasted words. However, given the lack of additional context, it could be considered overly minimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is incomplete for a deletion tool with no output schema. It does not cover return values, error conditions, permissions, or the effect on related entities, leaving the agent with insufficient context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (parameter descriptions exist in schema but the tool description does not mention parameters). The description adds no meaning beyond the schema, failing to compensate for low coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (archive/soft-delete) and the resource (collection in Metabase). It distinguishes from sibling tools like hard_delete_collection by specifying soft-delete.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. While 'soft-delete' implies it's reversible, there is no mention of prerequisites, when to choose this over hard delete, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description bears full responsibility. It does not disclose behavioral traits such as whether deletion is permanent, if it can be undone, or if permissions are required. The word 'Delete' implies a destructive action, but no further transparency is provided.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, one sentence long, and front-loaded with the action. It wastes no words. However, it could include more useful details in the same space, such as the irreversible nature or required permissions, which would improve completeness without adding bulk.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description is minimally adequate. It lacks contextual information like the effect on related entities (e.g., dashboard cards, tabs) or confirmation needed. For a destructive tool, more completeness would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'id' has a description in the input schema ('Dashboard ID to delete'), and the tool description does not add extra information. With schema covering the parameter, a baseline of 3 is appropriate. No additional meaning is provided by the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Delete' and the resource 'a dashboard from Metabase'. It distinguishes from sibling tools like delete_card or delete_action by specifying dashboards. However, it doesn't elaborate on the type of deletion (soft/hard) or effects, so it's clear but not maximally specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as delete_dashboard_public_link or archive_dashboard (if exists). The description does not mention prerequisites, alternatives, or context. For a destructive action, more usage guidance is expected.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose important behavioral traits such as irreversibility, required permissions, or cascading effects. Without annotations, this is a significant gap for a destructive operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded with the core action. Every word serves a purpose without unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and the destructive nature of the tool, the description is insufficiently complete. It omits details on side effects, permissions, or return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The sole parameter 'id' is described in the schema as 'Database ID to delete', achieving 100% schema coverage. The tool description adds no extra meaning, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('delete') and resource ('database connection'), distinguishing it from sibling delete tools for other entities. However, it lacks additional context about the specificity of 'database connection' in Metabase.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., update_database, get_database). It does not mention prerequisites or scenarios for deletion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states 'delete' without clarifying permanence, permissions, error handling, or side effects (e.g., whether it moves to trash or permanently deletes).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise. However, it omits essential information, so it is not optimally structured for clarity. It could be expanded without losing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description should explain return values or success/error behavior. It also lacks context about whether the operation is reversible, impacts analytics, or requires specific user roles.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the parameter 'id' only has a generic description 'Document ID'. The tool description adds no extra meaning or constraints (e.g., format, range, requirement that the document exists). The nested object structure is not explained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'delete', the resource 'document', and the method 'by ID'. It distinguishes from sibling tools like create, copy, get, and list documents by specifying the delete action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidelines on when to use or when not to use this tool. There is no mention of prerequisites, alternatives, or conditions under which deletion is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It states the deletion but omits whether it is permanent, if cascading effects occur, or if special permissions are needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the purpose. It avoids unnecessary words, though it sacrifices completeness for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool with one parameter and no output schema, the description lacks essential context such as return values, side effects, or confirmation. It is incomplete for an agent to use confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description for the 'id' parameter is clear ('Glossary entry ID to delete'), but the tool description adds no additional parameter context. With schema description coverage reported as 0%, the tool description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Delete a glossary entry from Metabase' with a specific verb and resource. It distinguishes the tool from siblings like create_glossary_entry and update_glossary_entry.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no prerequisites or conditions mentioned. The agent receives no context about when deletion is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description fails to disclose behavioral traits like destructive nature, required permissions, reversibility, or error handling. It only states the action without additional context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It is appropriately sized and front-loaded, though it lacks depth.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a mutation with one parameter, no output schema, and no annotations, the description is severely incomplete. It lacks information on effects, prerequisites, and safety, making it inadequate for safe invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% with the only parameter described as 'Table ID' in the schema. The description does not add any meaning or usage hints for the 'id' parameter beyond what the schema minimally provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (discard) and the resource (cached field values for a table). It distinguishes from sibling tools like 'discard_database_values' and 'discard_field_values' by specifying the table scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as 'discard_database_values' or 'discard_field_values'. There is no indication of prerequisites or scenarios where the tool is inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose any behavioral traits such as whether it is read-only, required permissions, or potential rate limits. For an export operation, the agent needs to know if it triggers a download or returns data inline, which is omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the purpose. It contains no fluff, though it could be expanded slightly to include context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a nested input object, the lack of output schema, and many sibling tools, the description is incomplete. It does not explain the document context, output format behavior, or differentiate from related export tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes each parameter (id: Document ID, card_id: Card ID, export_format: Export format). The description adds no additional meaning beyond what the schema provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Export' and the resource 'card query result from a document', which distinguishes it from tools that export card queries directly (e.g., export_card_query). However, it does not explicitly differentiate from other document-centric exports like export_document_card or export_public_document_card in sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. With multiple export siblings, the description should indicate scenarios (e.g., exporting from a document vs. directly from a card) but fails to do so.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It only states the action without describing any behavioral traits (e.g., read-only, authentication needs, side effects, or return format). The description adds minimal transparency beyond the tool's name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence without unnecessary words. However, it could be slightly more informative while remaining concise. It is well-structured and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description should at least hint at what the tool returns (e.g., form fields). It does not, leaving the agent uncertain about the tool's output. This is inadequate for a tool with one parameter and no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explain any parameters, and schema description coverage is 0%. While the input schema contains a description for the 'id' parameter, the tool description adds no extra meaning to help the agent understand parameter semantics or usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'Get the execute form fields for an action' with a specific verb ('Get') and resource ('execute form fields for an action'). This distinguishes it from sibling tools like 'get_action' or 'execute_action' by specifying the exact resource being retrieved.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or exclusions. Users must infer usage from the name alone, which is insufficient among many similar 'get_*' tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only states the read operation but omits potential issues like required permissions, what happens if the card doesn't exist, or return format. Minimal transparency for a retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no wasted words. However, it could benefit from a bit more structure (e.g., listing output or preconditions) without sacrificing conciseness. Still efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is too sparse. It does not clarify the type of return value (list of dashboards), error handling, or pagination. It is minimally adequate but lacks completeness for an agent to confidently use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for the top-level 'input' parameter, and the description merely rephrases 'a specific card' without explaining the id format or required structure. It adds little meaning beyond the schema's own property description ('The card ID').
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves dashboards containing a specific card, using a specific verb 'Get' and identifying the resource and filter. It distinguishes from siblings like 'get_dashboard' (single dashboard) and 'get_cards_in_dashboards' (reverse direction).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'get_cards_in_dashboards' or 'list_dashboards'. It does not mention prerequisites, excluded cases, or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description does not disclose behavioral traits like read-only nature, required permissions, or error handling. Fails to add any behavioral context beyond the verb 'Get'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, 12 words, efficiently conveys the core purpose. Front-loaded with verb and resource, no unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 parameters, nested object, no output schema, no annotations), the description is too brief. Missing return type details (PNG mentioned but no further), coordinate system explanation, and differentiation from sibling tile tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With schema description coverage at 0%, description must compensate but only provides high-level context (lat/lon fields). Does not explain tile coordinate system (x, y, zoom) or how they relate to the card, leaving parameter meaning unclear.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get', resource 'map tile PNG', and differentiator 'for a card with latitude/longitude fields', distinguishing it from siblings like get_table_map_tile or get_basic_tile.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_card_tile or get_table_map_tile. Description lacks explicit context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose safety and behavior. It only states the action without mentioning output format (likely an image), auth requirements, error handling, or rate limits. The agent cannot infer behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff. However, it might be too terse; a bit more detail could fit while remaining concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool returning a tile image with 4 parameters and no output schema, the description is too minimal. It omits crucial context like return type, coordinate system, and the fact that this is a read operation with potentially large data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already documents each parameter (x, y, zoom, card_id) with descriptions. The tool description adds no extra meaning beyond 'map tile' context, so it does not improve upon the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool retrieves a map tile for a card in Metabase. However, among siblings there are several tile-related tools (e.g., get_card_map_tile, get_table_map_tile) and no differentiation is provided, which slightly reduces clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_card_map_tile or get_basic_tile. No prerequisites, when-not-to-use, or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral traits like pagination, error responses, performance characteristics, or safety details. No annotations are present, so the description carries full responsibility for transparency, but it only states the basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at one sentence (10 words) and effectively communicates the core purpose. It is front-loaded and avoids unnecessary verbosity, though it could be slightly more descriptive.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with one parameter and no output schema, the description is adequate but lacks context about return values, list nature, or usage in dashboards. More detail would improve completeness given the lack of annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a clear description for the single parameter 'id' as 'Collection ID.' The tool description adds no further semantic meaning beyond what the schema offers. With full schema coverage for the parameter, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'dashboard question candidates' and specifies the scope 'from a collection in Metabase.' It distinguishes from siblings like 'get_root_dashboard_question_candidates' by mentioning collection context, though it does not explicitly contrast with other tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'get_collection_items' or 'get_root_dashboard_question_candidates.' There is no mention of prerequisites, filters, or situational context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description merely states 'Get timelines' without disclosing behavioral traits such as read-only nature, permissions required, or response format. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise single sentence. No fluff, but could benefit from slightly more detail. Front-loaded with the essential action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description lacks details on what is returned. Does not address common usage scenarios or disambiguate from related tools. Incomplete for a read operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema includes descriptions for all parameters (id, include, archived), but the tool description does not add any meaningful semantic detail beyond what the schema already provides. Baseline 3 due to high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get' and resource 'timelines' scoped to a specific collection. However, it does not differentiate from the sibling tool 'get_collection_root_timelines', potentially causing confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like 'get_collection_root_timelines'. No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behavior. It only says 'Get possible values' without mentioning auth requirements, error handling, or whether the operation is idempotent. The description is minimally informative about behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it lacks structured details. It is neither overly verbose nor efficiently packed with necessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of output schema, annotations, and the presence of multiple sibling tools, the description is insufficient. It does not specify return format, pagination, or any constraints, leaving the agent with incomplete context to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the description is the only source. It adds the phrase 'dashboard filter parameter' but does not explain the parameters beyond their names and types. The 'id' and 'param_key' have bare descriptions in the schema, but the description adds no additional semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get possible values for a dashboard filter parameter in Metabase', using a specific verb and resource. It distinguishes from sibling tools like get_card_param_values or get_embed_dashboard_param_values by focusing on dashboard parameters.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_card_param_values, get_embed_dashboard_param_values, or search_dashboard_param_values. The description lacks context on prerequisites or conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description does not disclose behavioral traits such as read-only nature, performance impact, or what the suggestions are based on.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, efficient and front-loaded with the key purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of autocomplete and no output schema, the description lacks essential details about how suggestions are generated, the format of results, or context for use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema includes descriptions for both 'id' and 'query', so the tool description adds no additional parameter meaning. Baseline score applies due to schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (get) and resource (card autocomplete suggestions for a database) but does not differentiate it from sibling tools like get_database_autocomplete or get_card_metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose what a healthcheck entails (e.g., test connectivity, check performance), whether it is read-only, or what happens if the database is unreachable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, concise and front-loaded with the purpose. However, it could be more structured, e.g., separate sentence for parameters or return value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description should clarify return value/effects. It lacks information on the healthcheck results (e.g., boolean, status report). Not complete for a tool with a single parameter and no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention the required parameter 'id' or add any meaning beyond the schema's 'Database ID'. The schema already provides the description, so no added value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Perform a healthcheck') and the resource ('database connection'). It differentiates from siblings like get_database (retrieve details) and validate_database (validate connectivity) by specifying the healthcheck operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs. alternatives (e.g., validate_database). No mention of prerequisites or context (e.g., database must be active).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states the action (get metadata) but does not mention side effects, permissions, or any constraints beyond the input ID. The description is minimal and leaves the agent uninformed about read-only nature or potential impacts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at one sentence with no unnecessary words. However, it could be slightly more structured to include key details like what the output contains.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks information about the output format or structure, which is important for a metadata retrieval tool. No output schema is provided, and the description does not clarify whether it returns tables, fields, or other nested information. Given the nested input schema, the agent may need more context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter 'id' exists with schema description 'Database ID', which is already in the input schema. The tool description does not add any additional meaning or context beyond what the schema provides. With 0% schema description coverage, the description should compensate but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves database metadata including tables and fields from Metabase. It uses a specific verb 'Get' and identifies the resource 'database metadata', distinguishing it from siblings like 'get_database' (basic info) and 'get_database_fields' (only fields).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_database' or 'get_table_metadata'. Lacks information about prerequisites or when it's appropriate to call.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must fully convey behavior. It suggests a read operation but does not explicitly state read-only, required permissions, or any side effects. It also fails to describe authentication or token validity implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no filler. It front-loads the main action and resource, but could be more structured to highlight the token requirement upfront.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without an output schema, the description should explain what the tool returns (e.g., card details, JSON data). It lacks this information, and given the many sibling tools, the role of this specific tool is insufficiently clarified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema description coverage is 0%, the description mentions 'by JWT token', aligning with the token parameter. However, it does not explain the nested input object structure or any additional validation rules beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get' and resource 'embedded card' with the required JWT token. It distinguishes from many related embed tools like get_embed_card_query or preview_embed_card, though the exact output (e.g., card data vs. metadata) is not specified.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No information on when to use this tool versus alternatives like get_embed_card_query or preview_embed_card. No prerequisites or exclusions are mentioned, leaving the agent to guess context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description gives no behavioral traits beyond the read operation. It does not disclose auth requirements, error conditions (e.g., invalid token), or performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no extraneous information. However, it could be slightly improved by including more context while remaining concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of embedded card parameter remapping, the many sibling tools, and lack of output schema, the description is incomplete. It omits return value structure, usage examples, and how it differs from similar tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the schema; it merely restates 'parameter of an embedded card'. With 0% schema description coverage for the top-level parameter, the description should compensate but fails. Inner parameter descriptions exist in schema, but the outer 'input' is undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Get remapping' and the resource 'parameter of an embedded card in Metabase'. It distinguishes from siblings like get_card_param_remapping (non-embedded) and get_embed_dashboard_param_remapping (dashboard vs card).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the many sibling tools (e.g., get_card_param_remapping, get_embed_dashboard_param_remapping). No mention of prerequisites such as needing an embed token or that this is for embedded cards specifically.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior, but it only states what the tool does, not how it behaves (e.g., error cases, authentication, rate limits). It adds no beyond-schema context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded. However, it is too brief and could include essential details without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested parameter, 0% schema coverage, no output schema), the description should provide more context about what values are returned and when this tool is appropriate. It falls short.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%. The description does not explain the parameters 'token' or 'param_key' beyond the schema's 'Embed token' for token. param_key is left undescribed. The tool's purpose vaguely implies param_key is the parameter key, but not explicitly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'values for a parameter of an embedded card in Metabase'. It distinguishes from siblings like get_embed_card_param_remapping by focusing on values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool instead of alternatives like get_embed_dashboard_param_values or get_card_param_values. The description lacks context for selectability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description does not disclose behavioral traits such as what kind of statistics are returned, permission requirements, performance implications, or response structure. The minimal description leaves the agent uninformed about the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence) but sacrifices completeness. It is front-loaded but does not contain all necessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the domain (many sibling field-related tools) and the lack of output schema, the description fails to explain what 'summary statistics' entails (e.g., count, min, max, distribution). The agent cannot determine if this tool meets its needs without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has low description coverage (0% per context signals). The description adds no additional meaning to the parameter 'id' beyond the schema's basic 'The field ID'. It does not specify format, constraints, or how the ID relates to summary statistics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), the resource ('summary statistics for a field'), and the context ('in Metabase'). It distinguishes itself from sibling tools like 'get_field', 'get_field_values', and 'get_field_related' by specifying 'summary statistics'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'get_field' or 'get_field_values'. There is no mention of prerequisites, scenarios, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Only states retrieval and optional filters; no mention of pagination, read-only nature, rate limits, or return structure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with purpose. Concise but trades off detail; no wasted words, but could include more guidance without harming conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and 0% schema description coverage, description fails to specify return format, pagination, ordering, or required parameter structure. Incomplete for an action with nested input.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% per context, but schema properties have descriptions. Description only mentions two of three parameters ('level' and 'namespace'), omitting 'last_n_lines'. Does not compensate for low coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'Retrieve' and specific resource 'application logs from Metabase' with optional filters. Well-differentiated from siblings like get_card or get_dashboard; logs are a distinct resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other logging or search tools. No prerequisites, context, or exclusions provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states what the tool does, not any side effects, permissions, or constraints (e.g., if the metric must exist, if it's read-only).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it lacks structure (e.g., no bullet points or separate sections). It is efficient but borderline under-specified for completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (single parameter, no output schema), the description is minimal but omits typical details like response format or prerequisites. For a basic get-by-ID tool, it's borderline adequate but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description adds minimal value beyond the schema's 'Metric ID' label for the id parameter. It doesn't clarify format, constraints (beyond schema's exclusiveMinimum and maximum), or usage notes.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get) and the resource (a specific metric by ID) in Metabase. It distinguishes itself from sibling tools like list_metrics and get_metric_dataset by focusing on a single metric retrieval by ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., list_metrics for multiple metrics, get_metric_breakout_values for typical data). No context or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It implies a read operation (name starts with 'get') but uses 'Run', which could indicate execution. It fails to mention side effects, permissions, idempotency, or error behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it concise, but it is overly sparse for a tool with a complex nested input. It lacks structure and essential details, falling short of being appropriately informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, annotations, and parameter details, the description is incomplete. It does not explain return values, the expected format of the metric definition, or any constraints, making it insufficient for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for the nested 'definition' parameter. The description only labels it as a 'metric definition' without explaining its structure or required fields. This leaves the agent uncertain about how to construct the input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: 'Run a metric definition as a dataset query in Metabase.' It specifies the verb ('Run'), the resource ('metric definition'), and the context ('dataset query'), effectively distinguishing it from sibling tools like 'get_metric' which retrieves definitions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'execute_query' or 'get_metric'. It lacks context about prerequisites, common use cases, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as required privileges, scope of permissions returned, or side effects. Relies entirely on the bare description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no redundant phrasing, but it lacks sufficient detail for complete understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema or annotations, the description is incomplete. It fails to clarify what 'permissions' entails—whether it's a list of permissions or assignments to resources.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the 'group_id' parameter with a clear description. The tool description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets permissions for a permission group. However, it does not differentiate from the sibling tool 'get_permission_group', which might return group details rather than permissions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives like 'get_permissions_for_db' or 'get_permission_group'. Missing context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description lacks behavioral details such as whether authentication is required, what happens with invalid UUIDs, or that it is read-only. Without annotations, this gap is significant.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence and concise, but it could be more informative without becoming verbose. It earns its place but lacks depth.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and only one parameter, the description is minimal. It does not explain what a 'publicly shared card' is or the expected response format, leaving gaps for an agent unfamiliar with Metabase.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explain the 'uuid' parameter beyond 'by UUID'. Although the schema includes a description for uuid, the top-level 'input' parameter is undocumented. The description fails to add value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a publicly shared card by UUID from Metabase. The verb 'Get' and resource 'publicly shared card' are specific, and it distinguishes from siblings like 'get_card' (private cards) and 'get_public_card_query' (query results).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'get_card' or 'get_public_card_query'. The description does not specify prerequisites or conditions, leaving the agent with no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states 'Get values', implying a read-only operation, but does not describe return format, error conditions, authentication requirements, or any side effects. Critical context for an agent is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no superfluous words. It front-loads the core purpose without any waste, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description is minimal. It conveys the essential read operation but lacks details on return values (e.g., whether it returns a single value or a list), error handling, or the relationship to public dashboard sharing. For a simple tool this might be acceptable, but completeness is only moderate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (the top-level 'input' parameter lacks a description, though its sub-properties have brief descriptions like 'Public sharing UUID' and 'Parameter key slug'). The tool description does not elaborate on parameter semantics beyond what the schema provides, missing an opportunity to clarify the role of 'uuid' and 'param_key' in a public dashboard context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get values'), the resource ('parameter in a publicly shared dashboard'), and the context ('from Metabase'). It is specific and unambiguous, but does not explicitly differentiate from sibling tools like 'get_public_dashboard_param_values' or 'search_public_dashboard_params', which might have overlapping functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its siblings (e.g., search_public_dashboard_params, get_public_dashboard_param_values). There is no mention of prerequisites, alternatives, or exclusions, leaving the agent to infer usage based solely on the tool name and brief description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a read-only fetch operation, which aligns with safe usage. However, with no annotations, it does not disclose any potential side effects, prerequisites (e.g., dashcard being public), or behavior under error conditions. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, efficient and to the point. However, it sacrifices necessary details for brevity, making it slightly under-specified. A few more words would improve clarity without harming conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested parameter, no output schema) and many sibling tools, the description is insufficient. It does not clarify the tool's role in the action execution flow, how it differs from similar get/execute tools, or what the returned values look like. Output schema is missing, and the description does not compensate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the description adds no value beyond the schema. The description does not explain the purpose of the nested parameters (uuid, dashcard_id, parameters) or how they relate to the tool's task. Schema descriptions exist for sub-properties, but the tool-level description provides no parameter context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Fetch' and resource 'values for executing an action on a public dashcard', which is specific. However, it could be more precise by clarifying that these are parameter values, and it does not clearly distinguish from sibling tools like 'execute_public_dashcard_action' or 'get_public_dashcard_query'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Among many siblings that involve public dashcards (execute, get query, etc.), the description does not explain the context for fetching values before execution. No when-not or alternative tools mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description lacks details about behavior beyond the verb 'get'. It does not specify what is returned (e.g., the entire collection object, metadata), whether authentication is required, or the effect of the empty input object. No annotations are provided to compensate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. It is efficient but could benefit from additional context without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is too brief given the tool's simplicity. It does not explain the empty input object, the return value, or how this tool fits into the broader collection hierarchy. An output schema is absent, so more description would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter 'input' with no properties, so the description adds no parameter information. Given the schema coverage is 0% but there are no properties to describe, the description is minimally adequate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the root collection, using a specific verb and resource. However, it does not distinguish from siblings like 'get_collection' or 'get_root_collection_items', which may cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For example, it does not mention that this tool does not require a collection ID, unlike 'get_collection', or that it returns the collection object itself rather than its items.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description should disclose behaviors. It only says 'get' without describing any side effects, permissions, or output nature. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One concise sentence, but could be improved by adding structured usage details. It is front-loaded and easy to read.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations, and many sibling tools. Description doesn't define 'related' or distinguish from other table getters, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema describes 'id' as 'Table ID', but tool description adds no additional meaning. With 0% schema description coverage, description fails to compensate for parameter context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets 'related tables and cards for a table in Metabase', specifying verb, resource, and context. This distinguishes it from siblings like get_table, get_table_foreign_keys, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. Does not clarify what 'related' means or when to prefer it over get_table_foreign_keys or get_table_metadata.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'Get query metadata', implying a read operation, but does not mention side effects, permissions, rate limits, or any other behavioral aspects beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no redundant information, earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is too brief for a tool with no output schema and no annotations. It does not explain what 'query metadata' entails, what the return value involves, or the purpose of the 'id' parameter, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% because the description does not mention the 'id' parameter. The schema itself has a description for 'id' (Table ID), but the description adds no additional meaning. The description must compensate for low coverage but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('query metadata for a virtual card-based table'), which distinguishes it from other metadata-fetching tools like 'get_card_metadata' or 'get_table_metadata'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not mention any conditions, prerequisites, or exclusions, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must convey behavioral traits. It only says 'Get', implying a read operation, but lacks details on safety, side effects, error conditions, or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It is concise but could benefit from slightly more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and no annotations, the description should at least hint at what 'X-ray dashboard candidates' are and what kind of data is returned. It fails to do so, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the parameter 'id' as 'Database ID'. The tool description adds no additional meaning or context beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'X-ray dashboard candidates for a database in Metabase'. It distinguishes itself from sibling xray tools by specifying 'database', and from other database tools by the unique resource type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get_xray_entity or list_databases. There are no statements about prerequisites, context, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only states what the tool does, omitting side effects, authentication needs, rate limits, or any other behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no extraneous information, making it concise. The use of 'automagic' is slightly informal but not wordy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has many closely related siblings and no output schema. The description fails to explain the return value, distinguish from other xray tools, or clarify what 'with a rule applied' means, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has nested parameters with descriptions (e.g., 'Entity type', 'Rule prefix'). The tool description adds no extra meaning beyond these schema descriptions, which is acceptable given schema coverage, but it does not compensate for the top-level 'input' parameter lacking a description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get' and resource 'x-ray automagic dashboard for a specific cell of an entity with a rule', making the purpose clear. However, the term 'automagic' is jargon and the description does not differentiate from similar sibling tools like get_xray_entity_cell or get_xray_entity_rule.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The sibling list includes many get_xray_* tools, and the description provides no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavioral traits. It implies a read operation but does not state side effects, authorization requirements, rate limits, or what happens if the rule does not exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded. However, it sacrifices depth for brevity; a slightly longer description could add value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has multiple required parameters, no output schema, and no annotations, the description is insufficient for an agent to understand the tool's behavior, return value, or how to construct the input object properly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description adds no parameter information beyond what the schema already provides. The schema includes descriptions for all four sub-properties, but the schema coverage is reported as 0% (possibly a misinterpretation). Baseline score of 3 is appropriate as the schema already documents the parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('x-ray automagic dashboard for an entity with a rule'). It distinguishes from sibling tools like get_xray_entity (no rule) and get_xray_entity_rule_compare (comparison). However, 'automagic' is informal and could be ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., get_xray_entity, get_xray_entity_rule_compare). There is no description of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully bears the burden of disclosure. It only states it lists tables, but fails to explain behavioral traits like permissions needed, whether virtual or hidden tables are included, or the output format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no unnecessary words. It fits the required format well.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is incomplete. It does not cover return structure, pagination, or any context about the data returned, leaving the agent without critical information for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema requires an object parameter with no properties, yet the description does not explain why this empty object is needed. Schema description coverage is 0%, and the description adds no insight into the parameter's purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'List' and resource 'all tables across all databases', clearly distinguishing it from siblings like list_databases or list_database_tables. The scope 'across all databases' is unique and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as list_database_tables or list_databases. The description gives no context for selecting this tool among many similar list_* siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states the basic function without mentioning that it is read-only, whether pagination exists, error conditions, or any performance implications. The agent lacks crucial information about how the tool operates.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise and front-loaded. However, it is too brief to be fully informative, sacrificing necessary details for brevity. It earns its place but could benefit from expansion.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and a single nested parameter, the description is incomplete. It does not explain the structure of the returned data (e.g., list of dashboard objects or IDs), pagination, or error handling. An agent cannot fully understand what to expect without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter 'input' containing 'card_ids'. The description merely paraphrases 'specified cards' and adds no additional meaning beyond the schema's own description ('Array of card IDs to look up'). With schema coverage effectively low (0% context signal), the description fails to compensate, missing details about format constraints or usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('dashboards that contain the specified cards'). The plural 'cards' distinguishes it from the sibling tool 'get_card_dashboards', which likely handles a single card. This provides specific verb and resource identification while differentiating from alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no guidance on when to use this tool versus alternatives like 'get_card_dashboards'. There is no mention of when not to use it, nor any context about prerequisites or preferred use cases. The agent receives no decision-making support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It only says 'List revision history' but does not describe output format, pagination, limits, ordering, or any side effects. For a read-only tool, this is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, no fluff, but it is too brief for a tool lacking annotations. It front-loads the action but omits critical details, making it minimally adequate.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description should compensate by explaining what the revision history contains (e.g., timestamps, users). It fails to do so, leaving the agent without important context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description adds no additional meaning for the 'dashboard_id' parameter beyond its schema description. It does not explain how to obtain the ID or any constraints (e.g., only valid dashboard IDs).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'revision history for a dashboard', with context 'in Metabase'. It is specific enough to distinguish from sibling tools like 'list_revisions' (generic) and 'get_entity_revision' (single revision), as it scopes to dashboards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'get_dashboard' for current state, 'list_revisions' for all revisions). No prerequisites or usage context provided beyond the parameter.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must shoulder the burden of behavioral disclosure. It only states 'List tables' without mentioning authentication needs, rate limits, side effects, or data freshness. The read operation is implied but not explicit, and no behavioral traits are described.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It efficiently communicates the core functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 required param, optional filter) but no output schema, the description is insufficient. It does not specify the format or content of the returned tables (e.g., names, metadata). More context about what 'list' returns is needed for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for both parameters (Database ID and Filter by schema). The description adds no additional meaning beyond what the schema states. With 100% schema coverage, baseline is 3, and no extra value is added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'tables in a database schema from Metabase', making the purpose understandable. However, it does not differentiate from similar sibling tools like 'list_all_tables' or 'list_database_schemas_with_tables', which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives is provided. The description does not mention when-not-to-use, prerequisites, or context. With many sibling tools focused on listing tables and schemas, explicit usage guidelines are needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description fails to disclose any behavioral traits such as pagination, filtering, authentication requirements, or data limits. The agent gets no insight beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence) but lacks structure and depth. It earns its place but fails to add value beyond the name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 0% schema coverage, the description should compensate but does not. It omits details about document types, response format, and potential limitations, making it inadequate for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter 'input' as an empty object, providing no structure or meaning. The description adds nothing about parameters, leaving the agent with no guidance on how to configure the call.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List all documents in Metabase', which is a specific verb and resource. It distinguishes from sibling tools like list_cards, list_dashboards, etc., by focusing on documents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. It does not mention exclusions or context, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only states 'List revisions' with optional filters, but does not disclose any behavioral traits such as pagination, ordering, permissions, rate limits, or side effects. Without annotations, this is insufficient for an AI agent to understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the core functionality without redundancy. It is front-loaded with the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, and the description does not explain what a revision object looks like or any specifics about the response. Additionally, it lacks guidance on pagination or limits, making it incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for both parameters ('id' and 'entity'), so the description adds no extra meaning. According to the rubric, with 100% schema coverage, the baseline is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and resource 'revisions in Metabase', and mentions optional filtering. However, it does not differentiate from siblings like 'list_dashboard_revisions' or 'get_entity_revision', which serve more specific purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, exclusions, or context for preferred usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description does not explain what happens to the moved cards, the target destination, permissions required, or side effects. The behavior beyond moving is opaque.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no redundancy. Could include more contextual information but remains concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one required nested parameter and no output schema, the description is too brief. It fails to explain the target collection or return value, leaving the agent with significant unknowns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is reported as 0%, but the schema does include a description for 'card_ids' ('Card IDs to move'). Description adds no additional meaning beyond the schema's minimal explanation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Move' and resource 'dashboard question candidates', and adds specificity 'from the root collection'. Distinguishes from siblings like 'move_cards_to_collection' and 'move_collection_dashboard_question_candidates' by specifying the source.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'move_cards_to_collection'. No prerequisites or context about the target collection are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should convey behavioral traits like read-only, permissions, or result limitations. It only says 'run a pivot query' without mentioning side effects, safety, or performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The single-sentence description is concise and front-loads the core purpose. However, it is too brief given the tool's complexity; a few additional phrases would improve completeness without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description omits what the query output contains, how to interpret results, or how parameters affect the pivot. Given the nested input schema and lack of output schema, this is insufficient for an agent to confidently invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter explanation beyond the input schema's minimal field descriptions (e.g., 'The card ID'). Since schema coverage is 0% (no tool-level param docs), the baseline of 3 is appropriate; the description merely confirms the tool's purpose without enriching parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Run') and the resource ('pivot query for a specific dashcard in Metabase'), distinguishing it from non-pivot variants like 'run_dashcard_query'. However, it does not explicitly contrast with sibling tools, losing a point.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'run_dashcard_query' or 'execute_card_pivot'). No prerequisites or context about dashboard/card relationships are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It states 'preview query results', which implies a read-only operation, but does not clarify side effects, rate limits, or what 'preview' returns (e.g., sample data vs. full results). This is minimal behavioral disclosure for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the essential purpose and constraint without extraneous words. It is appropriately sized for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has one parameter and no output schema. The description covers the core purpose and admin restriction, but it omits details about the output format (e.g., is it a table of rows? a count?). Given the low complexity, it is minimally adequate but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has one parameter 'token' with description 'Preview embed token', but the tool description adds no additional meaning or context for this parameter. With 0% schema description coverage (as reported), the description should compensate, but it does not mention parameters at all.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'preview', the resource 'embedded card', and the context 'by token from Metabase (admin only)'. It distinguishes the admin-only constraint, but doesn't explicitly differentiate from the sibling tool 'get_embed_card_query'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions 'admin only', which is a prerequisite, but provides no guidance on when to use this tool versus alternatives like 'get_embed_card_query' or 'run_preview_embed_card_pivot_query'. No exclusions or usage scenarios are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so description carries full burden. It merely restates the tool's action without disclosing permissions, side effects, or state change details (e.g., user becomes active).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no fluff, but could be more informative without becoming verbose. Concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Description lacks return value information, behavioral details, and context for decision-making. Although the tool is simple, the description is too minimal given the large set of sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides a description for the 'id' parameter ('User ID to reactivate'), so the description adds no additional meaning beyond the schema. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description provides a specific verb ('Reactivate') and resource ('previously deactivated user in Metabase'), clearly indicating the action. However, it does not differentiate this tool from siblings like 'update_user' which could also affect user status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Does not state prerequisites (e.g., user must be deactivated) or conditions for using it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only says 'revert', implying a destructive action, but does not disclose behavioral traits such as whether the operation is reversible, required permissions, side effects on related data, or if a new revision is created. With no annotations, the description carries full burden and fails to provide adequate context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that conveys the core purpose with no unnecessary words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a mutation with no output schema and no annotations, the description should provide more context about return values, side effects, and permission requirements. It lacks completeness for a revert operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not describe any parameters, so schema description coverage is 0%. However, the input schema itself provides detailed descriptions for each parameter (id, entity, revision_id), so the agent can understand them from the schema. Thus the description adds no value beyond the schema, but the schema suffices.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (revert), the resource (Metabase entity), and the target (previous revision). It distinguishes from more specific sibling tools like revert_dashboard by generalizing to any entity type, though it does not enumerate supported entity types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like revert_dashboard or list_revisions. There is no mention of prerequisites, or scenarios where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only states the basic action. It does not mention whether the query returns results, if it is read-only, what permissions are needed, or any side effects. The description lacks necessary behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that is front-loaded with the verb and resource. It contains no superfluous words and is easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and absence of an output schema, the description fails to provide essential context about return values, error conditions, or how this tool fits within the larger set of dashboard/card query tools. The schema covers parameter details, but behavioral completeness is lacking.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for all parameters (card_id, parameters, dashcard_id, dashboard_id), so schema coverage is high. The tool description does not add any additional meaning beyond the schema, thus meeting the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Run the query for a specific card on a dashboard in Metabase', using a specific verb and identifying the resource. However, it does not distinguish from closely related sibling tools like 'execute_dashboard_card_query' or 'run_embed_dashcard_query', which have similar purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as 'execute_card' for standalone cards or 'execute_dashboard_card_query' for dashboard card queries. There are no prerequisites or context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description should disclose behavioral traits. It does not mention that the operation is read-only, whether authentication is required, or any error conditions (e.g., invalid card ID).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 14 words, which is concise. However, it could be slightly improved by front-loading the primary action and including key constraints (e.g., card ID required).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is incomplete. It does not specify the return format, pagination, or behavior when no values match. The tool has many siblings, but no guidance on differentiation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% per context, meaning the schema does not adequately describe parameters. The tool's description adds no explanation of the 'input' object's fields (id, param_key, query), leaving the agent to infer from the names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource 'possible values for a card (saved question) filter parameter'. It distinguishes from sibling tools like search_dashboard_param_values and search_dataset_param_values by specifying 'card'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives like search_dashboard_param_values or search_embed_card_param_values. The description lacks any when-to-use or when-not-to-use hints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It does not disclose whether the tool is read-only, requires authentication, or has any side effects. The description is minimal and does not add behavioral context beyond 'search'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It is front-loaded with the core purpose. However, it could be expanded slightly to include usage context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is insufficient for an agent to fully understand the tool's behavior. It does not explain what the return value looks like, how filtering works, or any limitations. Sibling tools are numerous and similar, so more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for each sub-property ('Dashboard ID', 'Search query string...', 'Parameter key...'), which provide good semantic meaning. However, the top-level 'input' parameter lacks a description, and the tool description adds no extra clarification beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for possible values of a dashboard filter parameter. The verb 'search' and resource 'possible values for a dashboard filter parameter' are specific. However, it does not differentiate from similar sibling tools like 'get_dashboard_param_values' or 'search_card_param_values'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or conditions for usage. The description lacks any 'when-to-use' or 'when-not-to-use' information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits itself. It does not state whether the operation is read-only, whether it requires authentication, any rate limits, or what the response looks like. The single sentence lacks necessary behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence that is concise and front-loads the verb 'Search'. However, it is too brief and could benefit from more structure, such as listing the parameters or usage context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested parameter, no output schema, high number of siblings), the description is incomplete. It does not explain the purpose of the nested object, the role of each parameter, or what the search returns. The description fails to compensate for the lack of schema coverage and output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a nested object with three required fields (query, token, param_key), but the description does not explain the semantics or expected data types of these fields. Schema coverage is 0%, so the description adds no value in clarifying parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (search) and the resource (values for a parameter of an embedded card in Metabase). It effectively distinguishes this tool from siblings like search_card_param_values and search_dashboard_param_values by specifying 'embedded card'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as search_card_param_values or search_embed_dashboard_param_values. There is no context about prerequisites, when not to use, or scenarios where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for behavioral disclosure. It states the tool 'searches' but does not mention read-only nature, authentication requirements (JWT implied but not explicit), or side effects. The return format and pagination behavior are omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. However, it could be slightly expanded to include key usage notes without sacrificing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema, lack of output schema, and zero annotations, the description is insufficient. It fails to explain how this tool differs from similar search tools (e.g., search_embed_card_param_values) or what the response contains, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for the top-level 'input' property, though nested properties have descriptions. The description adds no extra meaning beyond the schema's own property descriptions (token, param_key, search_string). It does not explain constraints like token expiry or search string format.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and resource 'parameter values for a parameter in an embedded dashboard from Metabase'. It precisely distinguishes this tool from siblings like search_card_param_values (card context) or search_dashboard_param_values (non-embedded dashboard).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the many similar search siblings (e.g., search_embed_card_param_values, search_preview_embed_dashboard_param_values). The agent receives no help in deciding which search tool to invoke.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It only says 'search', implying a read operation, but does not explicitly state read-only status, idempotency, or any side effects. The description lacks important behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. However, its brevity sacrifices important context that could be structured for better clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description should explain return values, pagination, or behavior. It does not, leaving agents with insufficient information to use the tool effectively, especially given the numerous sibling search tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for all three parameters (id, limit, value), so the schema already covers their semantics. The tool description adds no additional parameter information, resulting in no added value but no detriment either.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'search' and the resource 'field values' within Metabase, but it does not distinguish this tool from multiple sibling search tools that also search for values in fields, such as search_measure_dimension_values or search_metric_dimension_values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternative search tools. There is no mention of prerequisites, context, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states "Search values" without mentioning if it's read-only, auth requirements, rate limits, or edge cases. This is insufficient for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence without unnecessary words. It is front-loaded with the action and resource, but could benefit from a bit more structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a nested object parameter and many similar sibling tools, the description lacks details on return format, pagination, and search behavior. It is incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 3 required properties with descriptions, achieving high schema description coverage. The tool description does not add extra meaning beyond that, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches values for a dimension of a measure in Metabase, using the specific verb "search" and resource. It distinguishes from siblings like get_measure_dimension_values and search_metric_dimension_values, though it doesn't explicitly contrast.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like search_metric_dimension_values or get_measure_dimension_values. The description provides no context on prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It only states that the tool sends immediately but does not disclose side effects (e.g., whether it triggers a real send), idempotency, permission requirements, or any other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no fluff. Every word contributes to the core purpose. Could slightly expand to include context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool with no output schema or annotations, the description lacks completeness. It does not mention return values, error conditions, or that the notification must exist, leaving the agent without sufficient context to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already documents the 'id' parameter with a description. The tool description adds minimal value by saying 'by ID'. Since schema coverage is effectively 100% (the parameter has a description), a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Send a notification immediately by ID in Metabase' clearly states the action (send) and resource (notification) with the scope of using an ID. It distinguishes from sibling 'send_adhoc_notification' by implication, but could be more explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'send_adhoc_notification' or 'get_notification'. No mention of prerequisites or that the ID must correspond to an existing notification.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations available, the description should disclose behavioral traits such as side effects, authentication requirements, or rate limits. It only states the basic purpose, leaving the agent unaware of potential impacts or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no unnecessary words. It is efficiently front-loaded, but the extreme brevity sacrifices valuable context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description is insufficient for an agent to fully understand the tool's behavior. It lacks details on what happens after submission, required authentication, or potential errors.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, and the description adds no additional meaning to the parameters beyond their names. The nested structure is not explained, and the description does not compensate for the lack of schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('submit') and the resource ('product feedback to Metabase'), making the tool's purpose immediately obvious. It is specific and distinguishes itself from sibling tools, as no other tool mentions feedback.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor are there any prerequisites or exclusions mentioned. The agent receives no context about appropriate scenarios for submission.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose behavioral traits such as whether testing sends a real notification, permissions required, or side effects. The word 'test' implies non-destructive but is ambiguous.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single concise sentence with no filler. While adequate, it could benefit from structured information (e.g., bullet points) for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and presence of schema descriptions, the description is minimally sufficient. However, lack of output schema and behavioral notes leaves gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes parameters 'type' and 'details' with brief descriptions, achieving high schema coverage. The tool description adds no additional meaning beyond what the schema provides, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'test' and resource 'notification channel configuration', distinguishing it from create/update/get channel siblings. However, it lacks detail on what 'test' entails (e.g., sending a sample notification or validating connectivity).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'test_email', 'test_pulse', or 'send_adhoc_notification'. The agent receives no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It only states 'translate' without disclosing side effects, permissions, reversibility, or what 'internal' and 'external' mean.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. It is front-loaded with the key action, though it lacks necessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of nested parameters, no output schema, and sparse annotations, the description is incomplete. It does not explain what 'internal' vs 'external' IDs are, which model types are supported, or the response format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no meaning to the parameters. It does not explain the structure of the 'input' object or clarify the 'entity_ids' array format beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific verb 'translate' and resource 'entity IDs', and provides context of internal/external representations in Metabase. It distinguishes this tool from all sibling tools, none of which perform translation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. No when-to-use, when-not-to-use, or exclusion criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a mutation ('disable'), but with no annotations, it fails to disclose important behavioral details such as required permissions, reversibility, or side effects (e.g., impact on cached data or query performance).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is front-loaded and effectively communicates the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the simple interface (one parameter), the description lacks completeness. It does not explain what 'disabling persistence' entails, such as whether the card remains available for queries or what happens to existing persisted data. The absence of any return value or error conditions further reduces completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not describe parameters, but the input schema provides a clear description for the only parameter ('card_id'). Since the schema covers the parameter semantics, the description adds no additional value, resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('disable') and the resource ('model persistence for a card/model'). It effectively indicates what the tool does, though it does not explicitly differentiate from similar tools like 'unpersist_database_models'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., 'enable_model_persistence', 'persist_card'). There is no mention of prerequisites, when not to use it, or example scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only says 'Unsubscribe from a notification', which implies a state change but fails to explain effects (e.g., idempotency, confirmation side effects, authentication needs). The description is too minimal for an agent to understand implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence with no redundant information. It is front-loaded with the verb and resource. However, it could include more detail without being verbose, so it scores high but not perfect.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, no behavioral annotations, and a nested input object, the description should provide more context about return values, prerequisites, and the optional email parameter. It only covers the basic action, leaving significant gaps for agent understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has descriptions for 'id' and 'email' sub-properties, but the top-level 'input' parameter has no description. The tool description only mentions 'by ID', adding no extra meaning beyond the schema. The optional 'email' parameter is not referenced, so the description does not compensate for the 0% schema description coverage at the top level.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'unsubscribe' and the resource 'notification by ID'. It distinguishes this tool from siblings like 'unsubscribe_notification_global' (which unsubscribes from all notifications) and 'undo_notification_unsubscribe' (which reverses), making it clear that this tool targets a specific notification by ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool vs alternatives. Siblings like 'undo_notification_unsubscribe' and 'unsubscribe_notification_global' exist, but there is no mention of appropriate contexts or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only says 'Unsubscribe' without explaining side effects, reversibility, or requirements (e.g., permissions). This is insufficient for an action that modifies state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, very concise. However, it could be better structured to include key information like side effects or usage hints.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without output schema or annotations, the description should provide more context, such as what happens after unsubscribing or the expected response. The minimal text leaves important gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The sole parameter `id` is described in the schema as 'The pulse ID', and the description adds no additional meaning. Schema coverage is effectively complete for this param, so the description does not need to add more.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'unsubscribe' and the resource 'pulse', making the action specific. However, it does not distinguish from sibling tools like `unsubscribe_pulse_email` or `undo_pulse_unsubscribe`, which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like `unsubscribe_pulse_email` or `undo_pulse_unsubscribe`. The description provides no context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It merely states the action without explaining side effects (e.g., moving children on parent_id change), permissions required, or whether the operation is idempotent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it concise but lacking detail. It is front-loaded with the key verb and resource, but the brevity leaves out important context that could be included without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters and a nested input object, the description is too sparse. There is no output schema, and the description fails to explain what happens when updating fields like archived or parent_id, leaving the agent without critical context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% - the description does not mention any parameters. Although the input schema has well-described parameters, the description adds no extra meaning beyond what the schema already provides. With no coverage, a higher burden to compensate is unmet.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it updates an existing collection in Metabase, specifying the verb 'Update' and the resource 'collection'. This distinguishes it from create and delete operations among siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or scenarios where it should not be used. Siblings like create_collection and delete_collection are present but no differentiation is offered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states 'update', implying mutation but disclosing no behavioral traits such as permissions required, side effects, idempotency, or return value. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence without redundancy. It is concise and gets straight to the point, though it could be slightly more informative without losing efficiency.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is incomplete. It fails to specify return values, required permissions, or behavior on failure. For a tool with nested input and no supplementary documentation, more context is needed for safe invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the description itself adds no parameter information, the input schema provides descriptions for 'id' and 'text' ('Comment ID to update' and 'Updated text content of the comment'), which adequately document the parameters. The description does not need to repeat this, but also does not add extra context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'existing comment in Metabase'. It effectively distinguishes from sibling tools like create_comment and delete_comment by using the specific action 'update'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., create_comment for new comments, delete_comment for removal). It does not mention prerequisites like having the comment ID.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It only states 'Update' without disclosing side effects (e.g., overwriting channels), required permissions, or behavior changes like archiving. The description is minimal and lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded with the action and resource, containing no wasted words. Efficient and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex nested input schema (with channels, schedule, recipients) and no output schema or annotations, the description is severely lacking. It provides no details on how the update works, what fields are required, or what the response looks like, making it insufficient for correct agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% according to context, and the description does not add meaning to the single 'input' parameter beyond its name. While sub-properties in the schema have descriptions, the tool description itself does not aid in understanding the parameter structure or usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update', the resource 'dashboard subscription', and specifies the type as 'email/Slack notification'. It effectively distinguishes from sibling tools like create_dashboard_subscription or delete_alert_subscription.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., creating a new subscription or deleting one). No prerequisites or context provided, such as requiring an existing subscription ID.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether the update triggers a sync, requires permissions, or the effect on connection state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with eight words, concise and front-loaded, containing no wasted information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations, the nested schema, and no output schema, the description is too minimal. It fails to explain return values, error conditions, or behavioral details needed for a mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all parameters (id, name, engine, details). The tool description adds no extra meaning beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'database connection configuration in Metabase', which distinguishes it from creation or deletion tools. However, it does not specify the updatable fields, but the schema covers that.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like create_database or delete_database. No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description only says 'update' without disclosing side effects, required permissions, or whether the entry must exist. Minimal transparency for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no unnecessary words or fluff, making it highly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple update operation, the description is clear but lacks details on return values, error states, or additional context like non-modifiable fields. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about parameters; while the schema has descriptions for each field, the tool description itself covers 0% of parameters and fails to summarize what input is expected.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (update) and resource (glossary entry in Metabase), distinguishing it from sibling tools like 'create_glossary_entry' and 'delete_glossary_entry'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no prerequisites (e.g., entry must exist), and no examples of when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'update' without mentioning side effects, required permissions, or idempotency. The schema hints at settable fields, but no behavioral context is added.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise, but lacks useful structure. It is barely adequate, leaving most details to the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input object with many optional/required fields, no output schema, and no annotations, the description is too minimal. It fails to explain update behavior or expected outcomes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% per context signal, and the description does not add meaning beyond the schema. The schema has descriptions but they are not counted; the tool description should explain parameter roles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Update LDAP authentication settings in Metabase' clearly uses a specific verb (Update) and resource (LDAP authentication settings), distinguishing it from sibling update tools like update_google_settings or update_slack_settings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives, prerequisites, or exclusions. Given many sibling update tools, explicit context would help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description merely restates the name. It does not disclose what exactly is updated (beyond schema fields), required permissions, reversibility, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no waste. However, it lacks structure and does not front-load critical information beyond the basic purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is a mutation with no output schema and no behavioral details. The description does not explain return values, side effects, or how it fits among sibling tools like 'list_memberships' or 'clear_memberships'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for 'id' and 'is_group_manager' with adequate clarity. The description adds no extra meaning beyond the schema. Baseline 3 is appropriate since schema coverage is effectively 100% for sub-parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('update') and resource ('permission group membership'). It distinguishes from 'add_membership' and 'delete_membership', but does not differentiate from 'update_permission_group' which updates the group itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'update_permission_group' or 'add_membership'. No prerequisites, context, or exclusions provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden for behavioral disclosure. It only states 'Update' but omits critical details such as idempotency, error handling (e.g., snippet not found), side effects, or return values. The schema partially covers input fields, but the description adds no behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with a single sentence, which is appropriate for a simple update operation. It is front-loaded and contains no fluff, but it could be slightly expanded to include a bit more context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (single input parameter with multiple nested fields), lack of annotations, and no output schema, the description is incomplete. It fails to mention expected return value, error conditions, or required permissions. Agents would lack sufficient context for reliable invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema_description_coverage is 0%, meaning the description should compensate for parameter meaning. However, the description only mentions 'Update an existing native query snippet' without elaborating on any of the input fields (e.g., which fields are updatable, constraints, or defaults). The schema itself provides adequate descriptions for each property, but the tool description adds no additional semantic value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and the resource ('existing native query snippet in Metabase'). It effectively distinguishes this tool from sibling tools like create_snippet, archive_snippet, get_snippet, and list_snippets, as it focuses on modifying an existing snippet.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as create_snippet or archive_snippet. It lacks context about prerequisites, typical scenarios, or conditions for appropriate use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral burden. It does not disclose whether admin privileges are required, whether sessions are invalidated, or if the change is logged. This is a mutation tool, and the description omits critical safety information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single efficient sentence with no wasted words. However, it could be improved by adding usage hints while remaining concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description omits return behavior, error conditions, or prerequisites. For a password update tool, the agent needs to know about constraints like old_password requirements, which are only hinted in the schema. The description leaves too much to inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already includes descriptions for all fields ('User ID', 'New password', 'Current password (required for non-admins)'). The description adds no extra value beyond the schema, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Update a user's password in Metabase' with a specific verb ('Update'), resource ('user's password'), and context ('Metabase'). It distinguishes itself from sibling tools like 'create_user_password_reset_url' (which creates a reset URL) and 'update_user' (which likely updates other fields).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'create_user_password_reset_url' for a reset workflow). No mention of required permissions or prerequisites like needing the old password for non-admins. The tool could be misused without these cues.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behaviors. It only states 'Delete' but does not mention if deletion is permanent, if there are cascading effects, or what the response indicates. Lacks essential safety context for a destructive operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise. However, it sacrifices necessary detail for completeness, balancing poorly for a destructive tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without annotations or output schema, the description should provide more context about the operation's effects (e.g., reversibility, dependencies). It is insufficient for an agent to safely invoke deletion.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for both parameters ('Segment ID to delete' and 'Message describing the reason for deletion'). The tool description adds no further semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Delete a segment from Metabase' clearly specifies the verb (delete), resource (segment), and system (Metabase). It differentiates from sibling tools like delete_card or delete_dashboard.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like delete_card or when not to use it. Prerequisites (e.g., user permissions) or conditions for safe deletion are not mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden but only says 'Get values'. It does not disclose that this is a read-only operation, any authentication requirements (public cards typically need no auth but not stated), or what happens on invalid UUID or param_key. No side effects or limitations are mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but overly minimal. It lacks important context that would make it more useful, such as parameter details or response format. It earns its place as a basic statement but could be improved.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and sparse description, the agent has little context about the tool's behavior. It does not explain what 'values' are returned, how the response is structured, or any constraints. This is insufficient for a tool with one complex parameter and no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high (both uuid and param_key have descriptions in the schema), so baseline is 3. The description adds no additional meaning beyond what the schema already provides, so score remains 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves values for a specific parameter of a public card, using a specific verb 'Get' and resource 'parameter of a public card'. It distinguishes from siblings like 'get_card_param_values' (non-public) and 'search_public_card_param_values' (search behavior), making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'get_embed_card_param_values' or 'search_public_card_param_values'. The description does not mention that it is for public cards exclusively or any prerequisites like knowing the card's UUID.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must convey behavioral traits. It implies a read-only retrieval but does not specify side effects, return structure, or authorization needs. The description is minimally adequate for a simple get tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, highly concise. However, it may be too brief, omitting important functional details, but it is well-structured and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a get tool with nested parameters for filtering and no output schema, the description should mention the filtering options. It provides the basic retrieval purpose but is incomplete regarding the full capability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention any parameters. Since schema description coverage is 0% per context, the description fails to add meaning beyond the schema structure. The filtering and include options are left undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a timeline by ID, which distinguishes it from list_timelines and get_timeline_event. However, it does not mention additional filtering capabilities via end, start, or include parameters, so it is not fully comprehensive.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like list_timelines or get_timeline_event. There is no mention of prerequisites or context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only states the basic operation without disclosing side effects, return format, or any constraints. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded with the key information. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one parameter, and the description covers basic purpose. However, the absence of an output schema means the agent may need more detail on return structure. Adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input parameter 'id' is described as 'Table ID' in the schema, but the description adds no additional meaning. Schema coverage is 0%, and the description does not compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'foreign keys for a virtual card-based table', distinguishing it from sibling tools like get_table_foreign_keys which likely handle regular tables.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., get_table_foreign_keys for regular tables). There is no mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It uses the vague term 'automagic dashboard' without explanation, and does not describe side effects, permissions, or output format. This leaves significant ambiguity for an AI agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but the term 'automagic' is unclear and could be replaced with more standard phrasing. It is front-loaded with the verb but the jargon reduces clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema and no annotations, the description is incomplete. It does not explain what an 'automagic dashboard' is, what the response contains, or any limitations. For a tool that retrieves a dashboard, more contextual details are needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for both inner parameters (model_index_id and pk_id), so the description adds little beyond noting 'by primary key'. The 'input' wrapper parameter lacks a description, but overall schema coverage is sufficient. Score is at baseline as the description does not detract nor significantly enhance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), the resource ('x-ray automagic dashboard for a model index'), and the method ('by primary key'). It distinguishes this tool from siblings like get_model_index, which likely retrieves the model index itself rather than a dashboard.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as get_xray_entity or get_xray_database_candidates. The description does not mention context, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden for behavioral disclosure. It only states 'List all API keys' but omits details on authentication requirements, permissions, pagination, or what the response contains (e.g., full details vs. keys only).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence, 5 words). It is appropriately sized for a parameterless tool, though it could benefit from a bit more detail on behavioral aspects without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters, no output schema, and no annotations, the description is minimal. It does not explain return format, pagination, or any constraints like admin-only access, leaving significant gaps for an agent to correctly use the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so schema coverage is 100%. The description adds no parameter information, but with no parameters to describe, this is acceptable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and resource ('API keys'), clearly stating the tool's action and distinguishing it from sibling tools like count_api_keys, create_api_key, etc. However, it does not specify any scope or filtering constraints.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. It does not mention when not to use it, what prerequisites exist, or how it relates to other listing or API key management tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose any behavioral traits (e.g., read-only, pagination, side effects). For a list operation, stating it is read-only would add value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 12 words, front-loaded with the main action. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple list operation but lacks details on output format, error conditions, or authentication prerequisites. No output schema to compensate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%. The description merely repeats 'database' from the schema, adding no meaning beyond the parameter's 'Database ID' description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'virtual tables (saved questions)', with the context 'available as tables in a database'. It effectively distinguishes from siblings like list_database_tables.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., list_database_tables, list_database_schemas). No prerequisites or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose whether the operation is read-only, requires authentication, or any rate limits. It only states it lists presets.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded and concise. No wasted words, but could briefly add value without bloat.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description lacks explanation of return format or what 'log level presets' are. It is minimally adequate for a simple list.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist; schema coverage is 100%. The description correctly implies no inputs are needed, meeting the baseline for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb+resource combination ('List available log level presets') and distinguishes from siblings like list_cards or list_users.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs other list tools. Does not explain the purpose of log level presets or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only states 'Update', implying mutation, but does not mention destructive potential, permission requirements, rate limits, or side effects. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise but lacks structure such as highlighting key constraints or front-loading critical information. It is adequate but could be more effectively organized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and only a one-line description, the tool is under-described. The agent lacks context on success/error behavior, idempotency, or post-update effects, making it incomplete for a field values update operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the parameters ('Field ID' and 'Array of [value, human_readable_value] pairs') with full coverage. The tool description adds no additional semantic value, so it meets the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool updates the 'human-readable values' for a field in Metabase, which is a specific verb-resource combination. It distinguishes this from sibling tools like 'get_field_values' (read) and 'update_field' (updates field metadata, not values).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'update_field' or 'search_field_values'. There is no mention of prerequisites, conditions, or exclusions, leaving the agent without context for appropriate invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states the core action but omits whether the operation is idempotent, if there are limits on tabs, required permissions, or side effects like reordering existing tabs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the core functionality and includes version context. No superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one input object with two fields) and no output schema, the description still feels incomplete. It omits details like the tab's position (appended?), behavior when dashboard doesn't exist, and relationship to siblings (e.g., removal/update).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage and the tool description does not elaborate on the parameters. It doesn't clarify that 'dashboard_id' must be an existing dashboard or constraints on 'name' (e.g., uniqueness, allowed characters).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add'), the resource ('a new tab'), and the context ('to a dashboard in Metabase (v0.49+)'). It distinguishes from sibling tools like remove_dashboard_tab and update_dashboard_tab by specifying creation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, prerequisites (e.g., dashboard must exist), or what happens if the tab name duplicates an existing one. The description lacks context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a destructive write operation but fails to disclose behavioral traits beyond what is minimal. Without annotations, it should mention side effects (e.g., if group becomes empty), permission requirements, reversibility, or impact on other entities.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that is front-loaded with the action ('Remove all users') and the resource. It is appropriately sized and contains no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description lacks completeness. It does not clarify the context of use, behavioral expectations, or what happens after removal, leaving the agent underinformed for a destructive operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description adds no meaning beyond the schema's parameter description, which already explains 'group_id'. With schema description coverage at 0% (likely meaning tool description doesn't cover parameters), the description does not compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Remove all users from a permission group in Metabase' uses a specific verb ('Remove all users') and names the resource ('permission group'), clearly distinguishing it from sibling tools like 'delete_membership' (removes a single user) and 'add_membership'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'delete_membership' or 'list_memberships'. It does not mention prerequisites, potential risks, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral traits such as mutation, authentication requirements, success/error responses, or side effects, which is critical given the absence of annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence. However, it sacrifices useful detail for brevity, placing it above average but not perfect.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input object, multiple engine options, and no output schema, the description lacks important context such as how to specify engine-specific details and the expected response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for name, engine, and details. The description adds no additional meaning beyond the schema, resulting in baseline adequacy.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Add a new database connection to Metabase' clearly states the action (add) and the resource (new database connection), effectively distinguishing it from sibling tools like create_card or create_dashboard.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like create_sample_database or update_database, nor are prerequisites or context mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description only states 'Create a dimension' without disclosing side effects, permissions, or reversibility. As a mutation tool, it lacks necessary behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, clear sentence with no unnecessary words. Efficiently conveys the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks information on return value, success criteria, and prerequisites (e.g., field existence). Given no output schema and no annotations, it is incomplete for a creation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no information about parameters beyond what is in the input schema. The description does not mention or clarify the expected 'id', 'type', 'name', or optional 'human_readable_field_id'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Create a dimension (remapping) for a field in Metabase', specifying the verb, resource, and context. It is distinct from sibling tools like 'delete_field_dimension' and 'get_field_remapping'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., creating a segment or metric). No prerequisites or use-case indicators are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'create' (implying mutation) but lacks details about permissions, idempotency, side effects, or what happens upon creation. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that efficiently conveys the core purpose. No filler words, perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having a nested input object and no output schema, the description provides no additional context about return values, limitations, or usage scenarios. It is too brief to be fully complete given the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is reported as 0%, so the description must compensate. However, it does not elaborate on any parameter beyond what the schema already provides. The input schema itself includes descriptions, but the tool description adds nothing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool's action: 'Create a moderation review' for Metabase items. It specifies the resource type ('Metabase item') and gives examples ('card, dashboard, etc.'), making it distinct from sibling create tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. No prerequisites, context, or exclusions are provided. The description only states what the tool does, not when it should be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only states the basic function. It does not disclose any side effects, required permissions, idempotency, or error conditions such as what happens if the name already exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single concise sentence with no extraneous information. It efficiently conveys the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the tool is simple, the description fails to mention what the output looks like (e.g., the created group object) or any account of valid name constraints beyond minLength. Missing return value information given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for the single parameter 'name' (described as 'Permission group name'). The tool description does not add additional meaning beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (create) and resource (permission group) with the context 'in Metabase'. It distinguishes from sibling tools like update_permission_group and delete_permission_group by using 'Create', but does not elaborate on the specific role or differences.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like update_permission_group or delete_permission_group. No prerequisites or context about permission groups mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only states the delete action but does not disclose behavioral traits such as whether the operation is idempotent, what happens if the link does not exist, or any side effects. For a destructive tool, more transparency is expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff, front-loaded with the key action and resource. Every word provides value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and minimal annotations, the description lacks completeness. It does not cover error handling, return format, or relation to other tools. For a tool with one parameter, it is too minimal.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (param description in schema is minimal). The tool description does not add any meaning beyond the parameter name and basic schema. It fails to compensate for low schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (delete), resource (public sharing link from a card), and context (Metabase). It effectively distinguishes from sibling tools like delete_dashboard_public_link or create_card_public_link by specifying 'from a card (saved question)'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like delete_dashboard_public_link or create_card_public_link. Lacks mention of prerequisites, idempotency, or error states. With many similar sibling tools, explicit context is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as destructiveness, permission requirements, or side effects. The agent must infer that deletion is irreversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise with one sentence that front-loads the verb and resource. However, it is overly minimal and could benefit from a bit more context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a delete operation with no annotations and no output schema, the description lacks information on prerequisites, error states, and reversibility, leaving the agent under-informed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the sole parameter 'id' as 'Document ID', so the tool description adds no additional value. Baseline 3 is appropriate despite 0% schema description coverage as per context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Delete' and the resource 'public link for a document', which distinguishes it from sibling tools like 'delete_document' and 'delete_card_public_link'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions mentioned. With many similar sibling tools, this is a gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It states 'Delete' which implies destructive action, but it does not mention reversibility, side effects on the field, or any prerequisites. The description lacks important context about what happens after deletion, making it insufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that clearly conveys the tool's purpose without any wasted words. It is concise and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one required parameter, no output schema), the description is moderately complete. It explains what the tool does but omits details about return values and the meaning of 'dimension'. For an agent unfamiliar with Metabase, additional context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a description for the 'id' parameter ('Field ID'). The tool description adds no additional meaning beyond the schema. Since schema coverage is high (the parameter has a description), a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete') and the resource ('a dimension (remapping) from a field in Metabase'). It is specific about what the tool does, distinguishing it from other delete tools by resource type. However, it does not explicitly differentiate from sibling tools like create_field_dimension, but the purpose is clear enough.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as when to create a dimension or get field remapping. The context of use is implied but not explicit, leaving the agent without clear decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It only states the action without revealing critical traits: whether deletion is irreversible, cascades to memberships, requires admin permissions, or has safety checks. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 5 words, placing the verb first. Every word earns its place, with no redundancy or filler. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation with no output schema, the description omits crucial context: confirmation, reversibility, error handling. It does not mention what happens if the group does not exist or if it has dependencies. The brevity leaves significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. Although the schema describes the 'id' parameter as 'Permission group ID', the tool description does not mention or clarify parameters. With 0% schema description coverage from the tool description, it fails to compensate for the gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete') and the resource ('a permission group from Metabase'), making the tool's purpose immediately obvious. It distinguishes itself from sibling tools like 'create_permission_group' or 'update_permission_group' by specifying the delete operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no prerequisites (e.g., group existence), and no mention of side effects or failure modes (e.g., if group has members). This lack of usage context forces the agent to infer appropriate conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks details about side effects, state changes, permissions required, or reversibility. The agent cannot infer behavioral traits beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It is front-loaded with key information. However, it could include more detail without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple toggle tool with no parameters and no output schema, the description is minimally adequate. It does not cover any prerequisites or effects, which might be acceptable given the tool's simplicity, but more context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the input schema is fully covered. The description adds the scope ('globally'), which provides additional context beyond the schema. Baseline for 0 parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('enable') and the resource ('model persistence') with a scope ('globally'). It is specific and distinguishes from the sibling tool 'disable_model_persistence' implicitly, though not explicitly naming it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the alternative 'disable_model_persistence' or other sibling tools. There are no explicit usage conditions, prerequisites, or exclusions provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states that the tool exports a result, omitting details about authentication needs, potential side effects (e.g., triggering a download), error cases, or the response format. This is insufficient for an agent to anticipate tool behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is exceptionally concise: one sentence of 14 words. It front-loads the key action and resource, and every word is necessary. No extraneous information or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and the rich sibling context, the description is minimally adequate. It correctly identifies the resource but does not help the agent distinguish among many similar export tools. Missing details like whether this is for private or public cards, or how the result is returned, reduce completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides clear descriptions for both parameters (id and export_format). The description merely repeats the enum values for export_format, adding no new semantic information. With high schema coverage, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Export), the resource (a card/saved question query result), and the available formats (csv, json, xlsx, pdf). However, it does not explicitly differentiate this tool from sibling export tools like export_dashboard_card_query or export_query, leaving some ambiguity for the agent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites such as needing a valid card ID or appropriate permissions. There are no explicit when-to-use or when-not-to-use instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavioral traits. It only says 'Get' with no mention of side effects, permissions, or what happens if parameters are invalid. The description is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (no output schema, nested parameter, no annotations), the description is too thin. It does not explain what 'remapping' is, what the output looks like, or any prerequisites like card existence.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (the top-level 'input' parameter lacks description), so the description must compensate. It does not explain what 'card_id' and 'param_key' represent or how they affect the remapping. The nested schema provides some meaning, but the tool description adds nothing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets a parameter remapping for a card in Metabase. It uses a specific verb and resource, and distinguishes from siblings like get_dashboard_param_remapping or get_dataset_param_remapping by specifying 'card'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as when to use get_dashboard_param_remapping. There are no prerequisites, context, or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It does not disclose any behavioral traits such as authentication requirements, error behavior, or side effects. It is a simple read operation but lacks transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that gets to the point with no wasted words. However, it could be slightly more informative without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should provide more context about what 'persisted model info' includes, but it does not. The description is minimal and leaves the agent guessing about return values or side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides a description for card_id ('Card ID to get persisted model for'), and the tool description adds little beyond that. With schema covering the parameter, the baseline is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (get), resource (persisted model info), and scope (for a specific card). It distinguishes from siblings like list_persisted_models and get_persisted_model.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. No mention of when not to use it or prerequisites. The description only states what it does.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states it is a 'Get' operation, implying it is read-only and safe, but does not explicitly mention idempotency, side effects, or any caveats.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no filler. It is front-loaded and efficient, though it could include more information without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (1 param, no output schema), and the description is adequate for a basic understanding. However, it lacks details on what 'related series data' includes or the structure of the response, which would be helpful given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the schema, which already defines 'id' as 'Card ID to get related series for'. Schema coverage is 0%, so the description fails to provide additional context for the parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('related series data for a card (saved question)'), making it distinct from sibling tools like 'get_card' or 'get_card_metadata'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as when to use 'get_card' or 'get_card_dashboards'. There is no mention of context or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the retrieval action without explaining side effects (none expected) or error behavior (e.g., 404 if not found). Minimal behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Front-loaded with key information. Could be slightly more informative without adding length, but efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is very sparse. It doesn't mention what the response contains (e.g., channel details) or any prerequisites. For a simple get operation, the agent might need more context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the parameter 'id' is described in the schema as 'Channel ID'. The description adds 'by ID', which is redundant. The schema already defines the parameter; the description adds no additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), the resource ('a specific notification channel'), and the identification method ('by ID'). It distinguishes from siblings like list_channels and create_channel.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., list_channels for all channels, create_channel for new ones). No when-not-to-use or prerequisite information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It implies a read operation but does not explicitly state that it is non-destructive or mention any potential side effects, authorization requirements, or data volume implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that directly states the tool's purpose without any unnecessary words or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of permissions graphs and the abundance of sibling permission tools, the description is too minimal. It lacks details about the output structure, filtering, or any key behavioral traits that would help an agent use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters, so no parameter documentation is needed. The description adds no param info, but the baseline for 0 params is 4, as the schema already covers everything.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a 'collection permissions graph' for all groups and collections, using a specific verb and resource. However, it does not explicitly differentiate from siblings like get_data_permissions or get_permissions_for_group, which are similar in nature.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternative permission-related tools. The description simply states what the tool does without any context or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states 'Get' without confirming idempotency, authentication requirements, or data sensitivity. This minimal disclosure is insufficient for a tool returning user data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It efficiently conveys the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple, but without an output schema, the description could mention that it returns the current user object (e.g., id, email, etc.). For a retrieval tool, this is adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter ('input') which is an empty object. Schema coverage is 0%, but since there are no actual properties to describe, the description adds no additional value. The schema itself already indicates no parameters are needed, so this baseline score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('the currently authenticated user'). It distinguishes from siblings like 'get_user' which requires a user ID, though it doesn't explicitly contrast them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_user' or 'list_users'. An agent would benefit from knowing that this tool requires no user ID and returns the caller's own user object.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as whether it is read-only, required permissions, error handling, or pagination. The agent receives no insight beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It is appropriately concise for a simple retrieval tool, though it could benefit from slightly more structured detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low tool complexity and single parameter, the description is minimally adequate. However, it lacks information about return values, possible error states, or any behavioral context, leaving gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% (per context), but the schema itself has a description for 'id'. The tool description does not add any additional semantic meaning or context beyond what is in the schema. For low coverage, the description should compensate but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), resource ('items (dashcards)'), and context ('of a dashboard in Metabase'). It distinguishes this tool from siblings like 'get_dashboard' and other retrieval tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Among many sibling 'get_' tools, there is no explanation of prerequisites, typical use cases, or when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description should disclose behavioral traits such as read-only nature, error handling, or authentication needs. It merely restates the operation without additional context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no fluff. However, it could be expanded with more context without becoming overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description fails to explain the concept of 'remapping', the return format, or any side effects. It is insufficient for a non-trivial operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add meaning beyond the input schema, which already provides descriptions for 'id' and 'param_key'. With schema coverage of 0% (meaning the tool description adds nothing), the default score is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific verb 'Get' and resource 'remapping for a parameter of a dashboard', and it distinguishes from sibling tools like 'get_card_param_remapping' or 'get_embed_dashboard_param_remapping' by specifying 'dashboard'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'get_dashboard_param_values' or 'get_embed_dashboard_param_remapping'). No prerequisites or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only says 'Get a measure by ID', implying a read operation but omitting behavioral details such as authentication requirements, error handling, or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise (one sentence), front-loaded with key information. However, lacks structural elements like bullet points or additional details that could improve readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description is minimally adequate. However, it could benefit from explaining what a measure is or returning value context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. It does not explain what a 'measure ID' is or how to obtain it, and schema coverage is 0%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get), the resource (measure), and how to identify it (by ID). It is specific and distinguishes from siblings like get_metric or get_card.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., get_metric, search_measures). The description provides no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits, but it only states the basic function. It does not specify whether the operation is read-only, requires authentication, or if it returns all values or just a subset. The description provides minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is front-loaded with the action and resource, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested input object, many sibling tools), the description is insufficient. It does not explain the nested structure, the format of 'param_key', or the return values (no output schema). The tool's definition lacks completeness for effective agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite the context stating 0% schema description coverage (though 'token' has a description), the description adds no additional meaning to the parameters. 'param_key' lacks any schema description or explanation of expected format/values. The tool's description does not compensate for the sparse parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves values for a parameter of a preview embedded dashboard in Metabase. It uses a specific verb ('Get') and resource ('parameter of a preview embedded dashboard'), distinguishing it from siblings like 'get_preview_embed_card_param_values' (card vs dashboard) and 'get_embed_dashboard_param_values' (non-preview).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'search_preview_embed_dashboard_param_values'. No prerequisites are mentioned (e.g., needing a valid preview embed token or a dashboard with parameters). The description lacks context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool gets a public dashboard but does not disclose behavioral traits like whether it is read-only (implied by 'get' but not explicit), error handling on invalid UUID, authentication requirements, or rate limits. The description is too sparse for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 8 words, delivering the core purpose without any filler. It is front-loaded with the verb and resource, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with no output schema, the description adequately states what the tool does but lacks details on return value format, error scenarios, or any additional context that would help an agent use it correctly. It is minimally viable but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has one parameter 'input' with a nested 'uuid' property. The schema provides a description 'Public sharing UUID' and a pattern for uuid. The tool description mentions 'by UUID', which aligns but adds no new information beyond the schema. Given 100% schema description coverage for the uuid property, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'publicly shared dashboard by UUID', making the tool's purpose clear. While it is distinct from siblings like get_public_dashboard_tile or get_public_dashboard_params, the description does not explicitly differentiate it, but the name and context suffice.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as other public dashboard tools or search tools. There is no mention of prerequisites, conditions, or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. Only states 'get details' without disclosing read-only nature, response structure, or any limitations. Minimal behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single concise sentence with no wasted words. However, it could be slightly expanded to include key information without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so description should explain return values. Only vaguely says 'details'. Does not mention what properties are returned or if nested objects exist, leaving agent uninformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% per context, but the schema actually includes a description for the 'id' parameter: 'The pulse ID'. The tool description adds no additional parameter meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get details of a specific pulse in Metabase', using the verb 'Get' and specifying the resource 'pulse'. It distinguishes from sibling tools like list_pulses (listing) and get_pulse_form_input (form input details).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like list_pulses or update_pulse. No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only states it 'gets' a value, implying read-only, but fails to disclose what happens if the key is missing, authentication requirements, rate limits, or any side effects. The minimal description lacks behavioral clarity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence. It is appropriately concise, but could include additional context without being verbose. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 parameter, no output schema), the description is minimally complete. It states the core function, but lacks usage guidelines and behavioral details that would improve completeness for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not add any meaning beyond the input schema. The schema already provides a description for the 'key' parameter. Since schema description coverage is 0% (the tool description does not describe any parameters), the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (get), the resource (single Metabase setting), and the mechanism (by key). It is specific and distinguishes from siblings like list_settings (which retrieves all) and update_setting (which modifies).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. For example, it does not mention that list_settings should be used to retrieve all settings or that update_setting modifies values. The description lacks context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only states 'Get', implying a read operation, but does not disclose any behavioral traits like required permissions, side effects, or what 'scheduler details' encompasses. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is front-loaded with the verb 'Get' and clearly names the resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should explain what the response contains. It only vaguely mentions 'task info and scheduler details'. Given the many task-related sibling tools, more details are needed for an agent to know if this is the right tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters are defined, so the schema coverage is 100% by default. The description does not need to add parameter information. Baseline is 4 for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves 'task info and scheduler details from Metabase', which is a specific verb-resource combination. It differentiates from sibling tools like get_task (likely single task) and list_tasks (list all) by including 'scheduler details', but could be more precise about whether it returns a summary or a list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_task, list_tasks, or get_task_run. No context about prerequisites or exclusion criteria. The agent is left to infer usage based on the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as required permissions, error handling, rate limits, or the nature of the response. It is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (9 words) and front-loaded with the purpose. However, it lacks any structural elements like expected output or additional notes.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (single parameter, no output schema), the description is minimally adequate but does not provide any context about task runs in Metabase or what the response looks like.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description does not elaborate on the 'id' parameter beyond what the schema provides. It adds no additional meaning or usage details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get), the resource (a single task run), and the identifier (by ID) and context (from Metabase). It distinguishes from sibling tools like list_task_runs and get_task.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. No prerequisites, when-not-to-use, or alternative tools are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should disclose behavioral traits like read-only, pagination, or ordering. It only mentions filtering, missing key aspects like whether all comments are returned or if there are limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is front-loaded with the core action and resource, then adds the filtering option concisely.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is straightforward with no output schema and simple parameters. However, it lacks information on return format, pagination, or order, which are common for list tools. It is minimally complete but leaves gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for both parameters ('model' and 'model_id'). The description adds minimal value by saying 'optionally filtered', which is already implied. With schema coverage effectively high, the description does not significantly enhance understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it lists comments, optionally filtered by model type and ID. The verb 'list' and resource 'comments' are specific, and it distinguishes from other comment tools like create_comment or delete_comment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. It does not mention prerequisites nor exclude cases like when filtering might not work. The sibling tools include many list_* tools, but no differentiation is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It does not disclose behavioral traits such as authentication needs, error handling (e.g., schema not found), rate limits, or response format. The description is purely functional without any behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that directly states the tool's purpose. It is front-loaded with the key action and resource, with no extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the tool's moderate complexity (nested input, no output schema), the description is too minimal. It does not cover expected output, pagination, or error scenarios. For a schema-specific table lister, this leaves the agent under-informed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the tool description does not mention any parameters or add meaning beyond the input schema. Moreover, the schema's description for 'schema' contains a misleading phrase 'Schema name to delete', which the description fails to correct or clarify.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'tables within a specific schema of a database in Metabase'. It effectively distinguishes this tool from siblings like list_all_tables (all tables) and list_database_tables (tables in a database without schema specificity).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, preferred contexts, or when not to use it. Given the many similar sibling tools, this omission is significant.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It only says 'list recent items', implying a read operation, but fails to define what 'recent' means, sorting, pagination, output format, or any limitations. Essential behavioral details are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded with the verb and resource, and includes the key modifier ('optional context filter'). Every word serves a purpose; no redundancy. Ideal conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has one parameter and no output schema, but the description does not explain what constitutes 'recent items' (e.g., time frame, item types) or the return format. It is adequate for a simple list operation but lacks completeness for efficient selection and use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal value over the schema, which already describes the 'context' parameter as 'Context filter (e.g., "views")'. The description simply restates the existence of an optional filter. Baseline 3 is appropriate for high schema coverage, but no additional clarification.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('List'), the resource ('recent items'), and the scope ('in Metabase'). It distinguishes from siblings like list_recent_views (specific views) and list_popular_items (popularity basis). The mention of optional context filter adds precision.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like list_recent_views or search. There are no explicit use cases, conditions, or exclusions. The description only states what it does, not when it should be chosen.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description bears full responsibility. It only mentions listing with optional filtering, but fails to disclose traits like pagination, response format, or result limits. This is minimal behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence without redundancy. It is front-loaded with the core purpose. Slightly more context could be added without harming conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and lack of output schema, the description adequately conveys the basic operation but omits expected return structure or any caveats. It is minimally complete for a list operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description adds no meaning beyond the schema's minimal 'Filter by archived status'. It does not clarify the parameter's effect or usage beyond echoing the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('list') and resource ('native query snippets') with an optional filter, making it unambiguous and distinct from sibling tools like 'archive_snippet' or 'create_snippet'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives or what scenarios it is best suited for. The description lacks usage context and exclusions, leaving the agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the behavioral burden. It only says 'list', but doesn't disclose ordering, pagination, whether it's read-only, or what constitutes 'recent'. Lacks essential details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with no unnecessary words. While minimal, it is appropriately concise for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple nature and no output schema, the description is partially complete. It fails to mention return format or limitations like maximum results, leaving gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the schema covers 100% of the trivial input. The description adds no parameter info, but none is needed. It could hint that the listing is unfiltered, but not required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists recent task runs in Metabase, using a specific verb and resource. However, it does not differentiate from sibling tools like list_tasks or get_task_run, which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_task_run or list_unique_tasks. The description provides no context about prerequisites or appropriateness.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a destructive action ('replace') but does not detail what happens to the existing table data, whether the table structure is preserved, permissions required, or limits on CSV size. No annotations are present to fill this gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded with the key action. However, it could be expanded slightly to include crucial details without losing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks critical context: how the CSV data is provided (file, content, etc.), what happens to the table schema, and any prerequisites. Without output schema or annotations, the description is insufficient for a destructive operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a description for 'table_id' (ID of the table to replace), and the tool description adds no further meaning. Since schema coverage is effectively 100% (despite context stating 0%), a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Replace'), the resource ('an existing table'), and the data format ('CSV data'), and distinguishes it from the sibling tool 'append_csv_to_table' which appends rather than replaces.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., append_csv_to_table), nor are any prerequisites or conditions mentioned. The agent is left to guess about proper usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only says 'trigger a rescan', which implies an action but does not clarify whether it modifies data, is idempotent, or has rate limits. The lack of detail on side effects makes it insufficient for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no unnecessary words. It front-loads the core action and resource, making it easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one parameter, so a short description is acceptable. However, the lack of output schema and absence of any return value explanation leaves the agent without knowledge of what to expect after invocation. This is adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes a description 'Field ID' for the single parameter, providing basic meaning. However, the tool description adds no additional context beyond what the schema already supplies. With minimal schema coverage, a score of 3 reflects adequate but not enhanced semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (trigger a rescan) and the resource (cached values for a field). It distinguishes from sibling tools like 'discard_field_values' and 'rescan_database_values' by specifying the scope is a single field's cached values, but does not explicitly call out differences.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'rescan_database_values' or 'search_field_values'. No prerequisites or side effects (e.g., performance impact, idempotency) are mentioned, leaving the AI without clear decision criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It fails to disclose behavioral traits such as read-only nature, authentication requirements, rate limits, pagination behavior, or default sorting. For a search tool, these are important for the agent to invoke correctly.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no redundant words. It front-loads the purpose and is appropriately sized for a straightforward search tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that the schema covers parameter details and there is no output schema, the description is somewhat complete for a basic search intent. However, it lacks information on pagination, result ordering, or behavior when no results are found. The tool has moderate complexity (nested object, multiple optional filters), so more guidance would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all parameters (q, limit, models, offset, table_db_id, collection_id), making schema coverage high. The description adds minimal value by listing entity types, which is redundant with the models enum. Therefore, baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches for cards, dashboards, collections, tables, databases, actions, and indexed entities in Metabase. It uses a specific verb and resource list, distinguishing it from sibling tools that search for specific parameter values (e.g., search_card_param_values). However, it could be more explicit about the scope (e.g., 'full-text search across Metabase').
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs. alternative search tools (e.g., search_field_values, search_card_param_values). The sibling list includes many specific search functions, but the description does not clarify that this is the general search tool covering multiple entity types.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description is minimal. It does not disclose behavioral traits such as search scope, filtering behavior, authentication requirements, rate limits, or whether results are ordered or limited.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence) and front-loaded. It is efficient but may be too terse for a tool with complex parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the nested input schema and lack of annotations or output schema, the description is insufficient. It omits details about how the search works, what values are returned, and how to construct the 'parameter' object.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for properties (e.g., 'Search query'), but the tool description adds no additional meaning. Baseline 3 is appropriate given schema descriptions exist; however, the description does not enhance understanding of the nested 'parameter' object.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (search), the resource (dataset parameter), and the system (Metabase). It distinguishes itself from sibling tools like search_card_param_values and search_dashboard_param_values by specifying 'dataset'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., get_dataset_param_values, search_card_param_values). The user must infer context from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It fails to clarify whether the search is read-only, the format of returned values, pagination, authentication requirements, or side effects. 'Search' alone does not convey sufficient behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 11 words, no fluff. It is efficiently structured and front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without an output schema, the description should hint at return value structure. It does not mention what kind of values are returned (list, single, etc.) or pagination behavior. For a search tool with nested parameters, this is inadequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must explain parameter meaning. It does not describe 'uuid', 'query', or 'param_key'. The names are suggestive but lack explicit semantics. An agent may guess incorrectly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource 'parameter of a public dashboard'. It distinguishes itself from sibling tools like search_card_param_values and search_dashboard_param_values by specifying 'public dashboard'. This provides unambiguous purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as search_dashboard_param_values or search_card_param_values. There is no mention of prerequisites, limitations, or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully convey behavioral traits. It only states what the tool does, omitting side effects (e.g., replacing existing schedule), permission requirements, rate limits, or error handling. This is insufficient for safe usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no unnecessary words. It is front-loaded and earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema, no annotations), the description is too minimal. It lacks details on cron format, return behavior, prerequisites, and potential errors, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The sole parameter 'schedule' is described in the schema as 'Cron expression for refresh schedule', but the tool description adds no additional meaning, examples, or format constraints. With 0% schema coverage reported, the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Set' and the resource 'refresh schedule for persisted models in Metabase'. It effectively distinguishes from sibling tools like 'refresh_persisted_model' and 'enable_model_persistence'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor are there any prerequisites, exclusions, or context about model persistence requirements. The agent receives no help on appropriate invocation scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description carries full responsibility for behavioral disclosure. It only states the action but omits critical details such as whether the operation is destructive, reversible, requires special permissions, or what the consequences are for the database and its models.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no extraneous information. It is perfectly front-loaded and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description still falls short. It lacks context about the relationship to sibling tools like 'persist_database_models', behavioral details, and any return values or side effects. More completeness is needed for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The sole parameter 'id' is described in the schema as 'Database ID'. The description reiterates this with 'for a database' but adds no extra constraints, formats, or purpose beyond what the schema already provides, which is minimal.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Unpersist all persisted models') and the target resource ('for a database in Metabase'). It effectively distinguishes from sibling tools like 'persist_database_models' (opposite) and 'unpersist_card' (single card), giving the agent a precise understanding of its function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For example, it does not mention that the sibling 'unpersist_card' handles individual models, nor does it specify prerequisites or scenarios where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It states a mutation (unsubscribe) but fails to disclose side effects, reversibility, or required permissions. The behavioral impact is unclear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately communicates the verb and the scope ('globally'). Every word adds value, and there is no unnecessary text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is minimally complete for a simple unsubscribe action. However, it lacks details on the 'hash' parameter's origin, the expected result, or error conditions. For such a simple tool, it's adequate but could be more helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for both 'hash' and 'email' parameters, so the description adds no new semantic value. Schema coverage is effectively high, leaving the description with little to contribute on parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (unsubscribe) and resource (email from all Metabase notifications). The term 'globally' hints at scope, but it doesn't explicitly differentiate from sibling tools like 'unsubscribe_notification' which may be per-notification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other unsubscribe tools (e.g., unsubscribe_notification, unsubscribe_pulse). The description implies a global action but does not specify prerequisites or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It merely says 'Update', but does not explain if the update is destructive, what permissions are required, or what the response contains. It adds no value beyond the verb.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that states the purpose without excess. It is appropriately concise for a simple update operation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is insufficient. It does not mention that only provided fields are updated, or that the 'id' is required. It fails to prepare the agent for common use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already contains detailed descriptions for all parameters (id, name, type, etc.). The description adds no parameter-specific guidance. Given high schema coverage, it meets the baseline for not detracting, but does not enhance understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and the resource ('existing notification channel in Metabase'). It effectively distinguishes from siblings like 'create_channel' and 'get_channel' by specifying the verb and object.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives (e.g., 'create_channel', 'test_channel'). It does not mention prerequisites (like needing the channel ID) or when not to use it. Sibling tools are given but no differentiation is made.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states 'Update', giving no information about side effects, permissions, idempotency, or what happens on success/failure. This is a significant gap for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that is front-loaded with the main action. However, it lacks structural elements like bullet points or sections that could improve readability for an AI agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with nested parameters and no output schema, the description is too minimal. It does not explain what a measure is, what fields can be updated, what the expected response is, or any prerequisites like existing measure ID. The agent would need to infer too much from schema alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for all three parameters (id, name, definition), providing adequate semantics. The tool description itself does not add parameter information, but with schema descriptions present, baseline score is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Update), the resource (measure), and the identifier (by ID). It distinguishes this tool from siblings like create_measure and get_measure, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., when to update vs. create or delete a measure). No prerequisites, conditions, or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist; description only says 'Update' implying mutation but omits any behavioral details like permissions, side effects, or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise single sentence, no redundancy. However, it underspecifies, making it less helpful than it could be.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input schema (nested objects) and lack of output schema, the description is too minimal to fully inform agent behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema's parameter descriptions are already detailed (e.g., 'The pulse ID'), so description adds no additional meaning. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Update' and resource 'pulse' within 'Metabase', distinguishing it from sister tools like 'create_pulse' and 'get_pulse'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use vs alternatives, prerequisites, or scenarios to avoid. Single sentence lacks context for choosing this tool over related ones.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only mentions what fields are updated but does not state side effects, permissions, idempotency, or potential impact on related data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, very concise and to the point. It is front-loaded with the action and resource, but could benefit from slightly more structure or detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and nested input, the description is insufficiently complete. It fails to mention return values, error conditions, or the scope of the update (e.g., partial update or full replacement).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the schema property descriptions are not considered sufficient. The tool description lists the updatable fields, which adds some meaning, but does not provide constraints or format details beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'table' and lists the specific updatable fields (display name, description, visibility). This distinguishes it from other update tools like update_card or update_dashboard.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives, nor any conditions or prerequisites. The description lacks context on appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only says 'Add a card', but does not indicate that this is a write operation modifying the dashboard, or any requirements (permissions, card existence). The minimal description leaves the agent unaware of side effects or prerequisites.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence of 10 words. No fluff, directly states the purpose and version. Excellent conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (10+ parameters with nested objects like virtual_card and parameter_mappings), the one-sentence description is insufficient. It does not explain key concepts such as the difference between real and virtual cards, tab assignment, or how parameter mappings work. The absence of output schema further increases the need for a richer description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides detailed descriptions for each parameter (e.g., col, row, size_x, virtual_card). The tool description adds no extra semantic value beyond the schema. With good schema coverage, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Add', the resource 'card', and the target 'dashboard'. It includes a version constraint (v0.49+), which is precise and distinguishes it from sibling tools like update_dashboard_card or remove_dashboard_card.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., add_dashboard_tab vs. this). There is no mention of prerequisites like the dashboard or card existing, or when to use virtual_card versus card_id. The description lacks context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states it returns a UUID but does not disclose behavioral traits like whether the link is publicly accessible, if authentication is required, or if it overrides existing links.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Front-loaded with the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple parameter and no output schema, the description is minimally adequate. However, it lacks details on permissions, side effects, and how the UUID is used.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite 0% schema description coverage, the description does not mention the input parameter at all. The schema itself describes the 'id' parameter, so the description adds no additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (create), the resource (public sharing link for a card), and the return value (UUID). It distinguishes from sibling tools like create_dashboard_public_link.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. Does not mention prerequisites or exclusions. For example, it does not say that the card must be saved or that the public link could be replaced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits like permissions, side effects, or whether the collection is immediately visible. The description adds no value beyond the obvious.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no unnecessary words. Front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations. The description is minimal and lacks details on return values, permissions, or error handling. For a creation tool with a nested input object, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover 100% of parameters (name, color, parent_id, description are explained). The tool description does not add any additional parameter semantics, so baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and resource 'collection (folder)' in Metabase. It distinguishes this from sibling tools like create_dashboard or create_card.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Among siblings, there are many creation tools, but no context on prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It mentions deletion but does not disclose permanence, side effects (e.g., cache invalidation), or error scenarios (e.g., link not found, permission denied). The phrase 'delete' implies destruction but lacks detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence (12 words) that front-loads the verb and resource. Every word carries meaning; there is no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should inform the agent about return values or response behavior. It does not. Additionally, it omits information about idempotency, error handling, and necessary permissions, leaving gaps for a deletion operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema describes the single 'id' parameter as an integer representing the action ID. The description adds no extra meaning beyond the schema. Since the schema coverage is sufficient for the single parameter, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete') and the resource ('public sharing link from an action in Metabase'). It effectively distinguishes from sibling tools like 'delete_action' (deletes the entire action) and 'create_action_public_link' (creates a link).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., delete_action) or prerequisites (e.g., the link must exist, user needs permissions). No context on when it is appropriate or when to avoid it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states 'Delete subscription' which implies a destructive action, but without annotations, it should disclose whether deletions are reversible, require authentication, or affect related data. No such behavioral details are given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence. It is appropriately concise with no redundant or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool with one parameter and no output schema, the description is minimally adequate. However, it lacks usage context and behavioral transparency, making it less complete for an agent to confidently invoke.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the description adds no parameter information beyond the schema. The sole parameter 'id' is documented in the schema, but the description does not compensate for the low coverage by clarifying the parameter's role or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Delete subscription to an alert in Metabase' clearly states the verb (delete) and the specific resource (subscription to an alert). It distinctly identifies the tool's action and distinguishes it from other delete tools in the sibling list, such as delete_dashboard_subscription or delete_pulse.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like delete_dashboard_subscription or other deletion tools. There is no mention of prerequisites, such as requiring ownership or permissions, nor when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits like idempotency, required permissions, or error handling. It only says 'delete' without any such context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that is front-loaded and contains no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and the presence of schema descriptions for nested parameters, the description is minimally adequate. However, it lacks behavioral context and completeness for a mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal value beyond the input schema. It hints at the model enum values but does not explain the parameters or their relationships. The top-level 'input' parameter lacks description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete) and the resource (bookmark) and specifies the types of items (card, dashboard, collection). It distinguishes from sibling delete tools that delete the items themselves rather than bookmarks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like delete_card or delete_dashboard. The description only states what it does, not when or why to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description fails to disclose behavioral traits like destructiveness, reversibility, or required permissions. Simply stating 'Delete' is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded and concise. However, it could be more informative without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation, the description is minimally adequate but lacks detail on return values or side effects. Given the lack of output schema, more context would help.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The parameter 'id' is described in the schema as 'Membership ID', so the description adds no additional semantics. With 0% schema description coverage as per context, the description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete') and the resource ('permission group membership in Metabase'). It is specific and distinguishes from siblings like 'add_membership' or 'clear_memberships'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'clear_memberships' or 'update_membership'. There is no mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only states it deletes an event, but does not clarify whether it is a soft or hard delete, if it triggers side effects, requires authentication, or is irreversible beyond the implied destructiveness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence of 8 words that is front-loaded with the verb and resource. No wasted words or superfluous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and simple delete operation, the description is too minimal. It omits common details like expected response (e.g., 204 No Content), idempotency, error handling, or confirmation of successful deletion. Sibling tools may have richer descriptions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with a description for the 'id' parameter. The tool description adds only the generic phrase 'by ID', which is redundant. Baseline 3 is appropriate as the schema already provides parameter clarity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'delete', the resource 'timeline event', the identifier method 'by ID', and the context 'in Metabase'. It distinguishes this tool from siblings like 'delete_timeline' (deletes a timeline) and 'create_timeline_event'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool, prerequisites, or alternatives. There is no mention of conditions under which deletion is allowed, or any warning about irreversible actions. The description is purely functional.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral details beyond the basic action. It does not state whether the operation is reversible, if it triggers a sync, or what the side effects are, leaving the agent uncertain about the impact.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence with no unnecessary words. It efficiently communicates the core purpose without fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is minimal but adequate. However, it lacks information about the return value (e.g., success/failure) and does not clarify that it is a destructive action, which would be useful for an agent
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description should compensate but does not add any parameter detail beyond what the schema already provides. The only parameter ('id') is not explained in the description, leaving no additional context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Discard'), the resource ('cached field values'), and the scope ('for a database'). It distinguishes from similar sibling tools like discard_field_values and discard_table_values by specifying the database level.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like discard_field_values or discard_table_values. There is no mention of prerequisites, consequences, or context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must bear full burden. It mentions AI usage but does not disclose reliability, performance, or potential side effects of the extraction. The description lacks detail on what 'extract table references' entails behaviorally.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the core purpose concisely. It front-loads the requirement and uses no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has nested parameters and no output schema, yet the description does not explain the output format, how template_tags work, or how the AI extraction behaves. More detail is needed for a complex tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema properties have descriptions (100% coverage), so the schema already explains the parameters. The main description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool extracts table references from a SQL query using AI, with a specific verb and resource. It also notes the requirement for Metabase Pro. This distinguishes it from sibling tools like execute_query or generate_sql.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions 'Requires Metabase Pro' as a condition but does not provide guidance on when to use this tool versus alternatives, nor does it explain when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It mentions AI usage and a licensing requirement, but fails to disclose whether the tool is read-only, what the output format is (e.g., SQL string), or if it executes the query. Behavioral traits beyond the basic premise are lacking.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a prerequisite tag, making it concise and front-loaded. However, it could be slightly more structured (e.g., separate the prerequisite) but is still efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema and lack of output schema/annotations, the description is incomplete. It does not specify what the tool returns (e.g., SQL query string), whether it executes, or dependencies like user permissions. The prerequisite is noted, but essential behavioral and output details are missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Context reports 0% schema description coverage, yet sub-properties of 'input' have descriptions ('Natural language question to convert to SQL' and 'ID of the database to query'). The tool description adds no additional parameter meaning beyond these; it does not explain the nested structure or clarify the role of the top-level 'input' parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Generate SQL from a natural language question using AI', specifying the verb (generate), resource (SQL), and input type (natural language question). It distinguishes this tool from all sibling tools, none of which offer NL-to-SQL conversion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description notes a prerequisite ('Requires Metabase Pro'), but provides no guidance on when to use this tool versus alternatives like execute_query or run_dashcard_query. Usage context is implied but not explicitly differentiated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only says 'Get details' without disclosing return format, side effects (likely read-only), error conditions, or other behavioral traits. This is insufficient for an unannotated tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence. However, it could include more useful information without becoming verbose. It is appropriately front-loaded but slightly under-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get tool with one parameter and no output schema, the description is minimal. It lacks details on output structure, error handling, and prerequisites. Given the many sibling tools, more context would aid selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides a minimal description ('The alert ID') for the single parameter. The tool description adds no additional meaning or context about the parameter, such as format, source, or how to obtain it. Given low schema coverage, the description should compensate but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get details' and the resource 'specific alert in Metabase'. It distinguishes from the sibling 'list_alerts' (which lists all alerts) and other get_* tools (which target different resources).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for retrieving a single alert by ID, but it does not explicitly provide guidance on when to use it vs. alternatives like 'list_alerts' for finding IDs, nor does it mention any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description does not disclose any behavioral traits such as permissions, performance implications, or side effects. Only states what the tool does.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded. It could benefit from slightly more structure, but it is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a simple tile retrieval, but it does not specify the output format (e.g., image data). Given no output schema, the agent might need more context on what the return value represents.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for all three parameters (x, y, zoom), so the schema already covers semantics. The description adds minimal value by summarizing 'by zoom level and coordinates', but it does not explain coordinate system or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'basic map tile', and the inputs 'zoom level and coordinates'. It distinguishes from sibling tools like get_card_tile or get_dashboard_tile by specifying 'basic'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_card_tile or get_dashboard_tile. No mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description should disclose behavioral traits. It only states the read operation but does not mention error handling, permission requirements, or potential side effects. The description is too minimal for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that immediately conveys the tool's purpose. Every word is necessary, and it is front-loaded with the key action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is adequate but lacks details on return format, error conditions, or when to prefer it over similar tools. It is minimally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema's id parameter already has a clear description ('Card ID to get metadata for'), and the tool description adds no further meaning about the input structure or usage. With 0% schema description coverage (excluding nested param descriptions), the description does little to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves query metadata (columns, types) for a card, which is a specific verb-resource combination. It also clarifies 'card' as 'saved question' and distinguishes from sibling tools like get_card (which retrieves card details) and get_card_param_values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. Among many get_* sibling tools (e.g., get_card, get_card_param_values, get_card_series), there is no explicit context for selecting this one.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of disclosing behavioral traits. However, it only states the basic action without mentioning side effects, permissions, or whether it's a read-only operation. The description lacks transparency about what the tool does beyond its stated purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately communicates the tool's purpose. There is no redundant or extraneous information, making it highly efficient and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description should provide context about the return value. It does not describe the hierarchical tree structure's format or content. For a tool with no parameters, the description is insufficiently complete to fully inform an agent about the expected output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters, so schema coverage is 100% trivially. The description does not need to add parameter information. It adds no additional meaning beyond the schema, earning the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to retrieve the hierarchical tree structure of all collections in Metabase. It uses a specific verb ('Get') and defines the resource precisely, distinguishing it from siblings like 'get_collection' (single collection) and 'get_collection_items' (list items in a collection).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. Among sibling tools like 'get_collection', 'get_collection_items', and 'get_root_collection', there is no mention of scenarios or exclusions, leaving the agent to infer usage without support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description offers no behavioral details beyond 'get all fields'. It does not disclose whether the operation is read-only, if it fetches field metadata or values, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that communicates the purpose without any unnecessary words or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is minimal and lacks information about the return format (e.g., whether it returns field names, types, or nested details). With no output schema and no annotations, the agent is left without sufficient context to fully understand the tool's response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'id' is already documented in the schema with the description 'Database ID'. The tool description does not add any additional meaning or context about how to use the parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Get all fields for a database in Metabase'. It specifies the verb (Get), resource (fields), and scope (for a database), distinguishing it from sibling tools like 'get_database' or 'get_table'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'get_table' or 'list_database_tables'. There is no mention of context, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It indicates a read operation ('Get query results') but lacks details on auth requirements beyond mentioning JWT, potential rate limits, or side effects. It does not contradict any annotations (none provided), but it is minimal for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no redundancy. It is front-loaded and efficient. However, it lacks any structure (e.g., bullet points) that could improve scannability for a tool with nested parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description is partially complete. It explains what the tool does but does not describe the return format or the prerequisite that the embed card must be set up. More context would help an agent understand the full flow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, so the description carries the burden. It adds that the token parameter is a 'JWT token', which provides context beyond the raw schema. However, it does not elaborate on the token's format or required permissions, so only moderate added value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and resource 'query results for an embedded card', distinguishing it from sibling tools like get_embed_card (metadata) or export_embed_card_query (export format). However, it does not explicitly differentiate from other similar query tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites, conditions, or when not to use it. It is a single sentence without contextual advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description should disclose behavioral traits. It does not mention read-only nature, required permissions, rate limits, or return characteristics. The description is minimal and fails to add context beyond the basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no fluff. It efficiently conveys the core purpose, though it could be slightly expanded without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read operation with one parameter and no output schema, the description is minimally complete. However, it lacks any mention of return format or potential errors, which would be expected for completeness in an API context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema fully describes the single 'id' parameter with type and constraints. The description adds nothing beyond 'by ID', which repeats the schema. Since schema coverage is 100% for parameters, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get), the resource (specific persisted model), and the method (by ID). It effectively distinguishes from sibling tools like list_persisted_models (list all) and get_card_persisted_model (different context).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus other get/list siblings. No 'when to use' or 'when not to use' context is given, leaving the agent without decision support for sibling differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only states the basic operation without disclosing important behavioral traits like authentication requirements, whether the card must be public, rate limits, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is direct and free of extraneous information. It is appropriately concise for the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and the existence of many similar sibling tools, the description could be more complete by clarifying preconditions (e.g., the card must be publicly shared) or differentiating from export_public_card_query_format. However, it minimally covers the essential purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the top-level parameter 'input' lacks a description. The nested parameters (uuid, export_format) are described in the schema, but the tool description adds no additional meaning or context beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'query results for a publicly shared card', and the specific aspect 'in a specific export format'. It distinguishes from siblings like get_public_card_query by adding the format parameter.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving query results in a given export format but does not explicitly state when to use this tool over alternatives such as export_public_card_query_format or get_public_card_query. No when-not or alternative guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations and no behavioral details provided. The description does not mention authentication, rate limits, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key information, but could include minor additional context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and missing details about prerequisites (e.g., how to obtain uuid and param_key) make it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain the 'uuid' and 'param_key' fields beyond their names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Get values for a parameter of a public dashboard' in Metabase, distinguishing it from similar tools for non-public dashboards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives, though the name 'public' implies it's for public dashboards.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility but only states the basic retrieval action. It does not disclose read-only nature, error conditions (e.g., invalid UUID, not found), or safety information. Minimal transparency for a simple get tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently communicates the purpose. It is front-loaded with the key information and contains no redundant words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description covers the basic action and identifier. However, it omits details about the return format and emphasizes 'publicly shared' but does not clarify if any authentication is required, leaving some gaps for an agent deciding to use it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions UUID, which matches the schema parameter, but does not explain the nested structure or add meaning beyond the schema description of the uuid field. Schema coverage is 0%, and the description fails to compensate for this gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get), the resource (publicly shared document), the identifier (by UUID), and the source (from Metabase). It is specific and unambiguous, distinguishing it from similar tools like get_document or get_public_document_card.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It simply states the function without context, leaving the agent to infer usage from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only states the action without disclosing behavioral traits such as side effects, authentication requirements, or error conditions (e.g., what happens if the document is not publicly shared). The read-only nature is implied but not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that efficiently communicates the tool's purpose without extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a nested input schema, no output schema, and no annotations. The description does not explain what a 'card' is in this context, how to obtain the UUID or card_id, or what the return format is. It lacks sufficient detail for an agent to fully understand the tool's usage and expectations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for both uuid and card_id, so the tool description adds little beyond the context of 'publicly shared document'. However, the description does not explicitly explain the role of card_id (e.g., whether it's the card's ID or a number within the document). Given the schema's coverage, the description provides minimal additional value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get a card from a publicly shared document by UUID in Metabase' clearly specifies the action (get), resource (card), and context (publicly shared document by UUID). It distinguishes itself from siblings like get_public_card and get_public_document, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives such as get_public_card or get_public_document. No explicit conditions, prerequisites, or when-not-to-use instructions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It correctly implies a read operation but fails to mention any potential side effects, permissions, or error handling. The minimal description leaves gaps in behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at 12 words, front-loaded with the key action and resource. No superfluous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with one parameter, the description is adequate but could mention the return type (e.g., 'Returns a snippet object') or that the ID is required. Given the absence of an output schema, this minimal info is functional but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description should compensate by explaining parameters. However, it does not mention the 'id' parameter at all. The schema itself describes the 'id' field, but the description adds no value beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'native query snippet', and the scope 'by ID'. It distinguishes this tool from siblings like 'list_snippets' and 'get_native_query' by specifying 'snippet' and 'by ID'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'list_snippets' or 'get_native_query'. The agent must infer usage solely from the name and parameters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as idempotency, required permissions, or whether the operation is safe and read-only. This gap leaves the agent uninformed about important invariants.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with 9 words, front-loading the action and resource. No unnecessary content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with no output schema, the description is minimally adequate. However, it could mention that the tool returns the value or null, which would improve completeness without adding bulk.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the input schema provides no parameter descriptions. The description only mentions 'namespace and key' without adding any details about formats, constraints, or examples. The description does not compensate for the missing schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (get), the resource (per-user key-value preference), and the retrieval method (by namespace and key). It is distinct from related siblings like put_user_key_value and delete_user_key_value.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as list_user_namespace_values or put_user_key_value. The description lacks context about typical scenarios or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits like side effects, data scope, or authentication needs. It only states the basic action without explaining what happens when listing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that captures the essential purpose. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks details on the output format, pagination, or filtering behavior. Given the tool has nested objects and required input, more context would be beneficial for correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for both parameters (archived, dashboard_id), providing sufficient meaning. The tool's description adds no additional parameter information, so scoring at baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists dashboard subscriptions, specifying 'email/Slack notifications' and the context 'in Metabase'. It uses a specific verb and resource, distinguishing it from sibling tools like list_dashboards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or related tools such as create_dashboard_subscription.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states a requirement and the basic action, but does not disclose whether the operation is read-only, safe, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the requirement, but could be slightly more structured to include behavioral context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no parameters and no output schema, the description fails to mention return format or pagination behavior, leaving an agent without essential context for a list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is 100%. The description adds value by noting the prerequisite, which is beyond the schema, meeting the baseline for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'available AI/LLM models configured in Metabase'. It adds a prerequisite (Metabase Pro) which helps differentiate from other tools, but does not explicitly compare with siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when listing LLM models and states the Pro requirement, but lacks explicit guidance on when to use this tool versus alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only states 'list all' without mentioning pagination, authentication requirements, or whether it returns a list of memberships for all groups or other details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise, front-loaded sentence that wastes no words. It efficiently communicates the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no parameters and no output schema, but the description does not specify the return format or any pagination behavior. While it is simple, it leaves gaps for an agent needing to interpret the response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters in the input schema (100% coverage). Per guidelines, for 0 parameters the baseline is 4. The description adds no further parameter info, but none is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all permission group memberships in Metabase, using a specific verb and resource. However, it does not differentiate from sibling tools like list_permission_groups, which lists groups themselves.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as add_membership, delete_membership, or list_permission_groups. The description does not include any when/when-not or alternative tool references.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It states a read-only operation, but it does not mention whether results are paginated, if any side effects exist, or if authentication is required beyond 'admin only'. The lack of detail on common list operations reduces transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the key information. However, its brevity omits necessary details about parameters and behavioral expectations, making it slightly under-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotation support, the description is incomplete. It lacks information on output format, pagination, filtering, and any prerequisites or limitations beyond 'admin only'. A more complete description would include these aspects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a required 'input' object with no properties, but the description does not explain its purpose. With 0% schema documentation coverage, the description should compensate, but it provides no parameter guidance at all.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all cards with public sharing links and includes 'admin only' to specify access level. It distinguishes from siblings like list_cards and list_embeddable_cards by focusing on public sharing links.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'admin only' constraint provides clear context for usage, but there is no explicit guidance on when to use this tool versus alternatives like list_cards or list_embeddable_cards. The purpose is clear enough for an agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral details like side effects, return format, or what 'recent' means (e.g., time window, ordering). The agent has little beyond the basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no wasted words. Six words convey the essential purpose efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a parameterless list tool but leaves ambiguity about what constitutes 'recently viewed' and the output format. Given no output schema, more detail could help.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, and schema coverage is 100%. With no params, the description does not need to add semantics; baseline is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'list' and the resource 'recently viewed items' with context 'Metabase'. However, it does not differentiate from the sibling tool 'list_recents', which could be similar.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, such as 'list_recents', is provided. The description only states the function without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description lacks behavioral details such as read-only nature, permission requirements, pagination, or scope (e.g., current user vs. all users). The description only states the action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no unnecessary words. Front-loaded with verb and resource. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple list operation with no parameters. However, lacks context on what constitutes a 'scheduled task' or whether it includes all users' tasks. Could be more precise.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters, schema coverage is 100% and description adds no parameter info. Baseline for 0 params is 4, though description adds nothing beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List all scheduled tasks in Metabase,' specifying the verb (list) and resource (scheduled tasks). However, it does not differentiate from siblings like 'get_task' or 'list_unique_tasks'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. For example, it does not contrast with 'get_task' (single task) or 'list_task_runs' (task run history).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description is minimal. It implies a read-only operation but does not disclose any side effects, authorization requirements, or limitations. For a list operation, more detail (e.g., return format, pagination) would be helpful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at 8 words, with no unnecessary information. Every word carries meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one parameter, no output schema), the description is adequate for basic understanding. However, without annotations, additional context about return behavior or auth would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a description for the 'namespace' parameter. The tool description does not add additional meaning beyond what the schema offers. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool lists key-value pairs in a per-user namespace. It distinguishes from sibling 'get_user_key_value' which retrieves a single key-value, but does not explicitly mention that distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like 'get_user_key_value'. No mention of prerequisites or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'Set', implying mutation, but does not explain side effects, required permissions, or whether it overwrites or merges existing configuration. The schema provides some structure but no behavioral insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is direct and free of superfluous information, earning its place without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of an output schema and the presence of sibling tools for cache configuration (get, delete), the description is too brief. It fails to explain the outcome of the operation, such as whether it updates an existing config or what happens on conflict, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for each property (model, model_id, config, strategy), covering their types and meanings. The description adds no additional semantic value beyond what the schema already provides, resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Set the query caching configuration in Metabase' clearly indicates the verb (Set) and the resource (query caching configuration). It distinguishes from sibling tools like get_cache_config (read) and delete_cache_config (delete).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as get_cache_config or delete_cache_config. There is no mention of prerequisites, whether it creates or updates, or any context for appropriate use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden of behavioral disclosure. It only says 'update' without mentioning side effects, permissions, idempotency, or error handling (e.g., what happens if the key does not exist). Minimal behavioral context beyond the action itself.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is clear and to the point. No unnecessary words, but it could be slightly more structured with additional context while remaining concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and incomplete parameter documentation, the description is too brief. It does not cover return values, error states, prerequisites, or behavior for missing keys. For a simple update tool, it is minimally complete but lacks depth.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 2 parameters: 'key' (with a description) and 'value' (without). The description adds no additional meaning beyond 'by key', and does not explain the 'value' parameter. Schema description coverage is 0% at the top level, and the description does not compensate for the missing parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'update' and the resource 'a single Metabase setting by key', distinguishing it from sibling tools like 'bulk_update_settings' which updates multiple settings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for updating one setting by key, but does not explicitly specify when to use this tool vs alternatives like 'get_setting' to view a setting or 'bulk_update_settings' for batch updates. No exclusion criteria or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. However, it only states 'Update an existing timeline' without detailing side effects, permission requirements, return value, or any mutation characteristics. The agent gains no insight beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no extraneous information. It is well front-loaded and conveys the core purpose without waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having a clear purpose, the description lacks completeness for an update operation with a nested input object. There is no mention of output (e.g., returns the updated timeline), error conditions, or any behavioral specifics beyond the schema. The absence of annotations and output schema places a higher burden on the description, which it does not meet.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for all parameters (id, icon, name, archived, description, collection_id), providing high coverage. The tool description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action ('Update an existing timeline') and the resource ('timeline'), with context ('existing') that distinguishes it from create_timeline and delete_timeline. The verb-resource combination is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as create_timeline or get_timeline. There is no mention of prerequisites (e.g., the timeline must exist) or comparisons with sibling tools, leaving an agent to infer usage context on its own.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behavior. It does not mention side effects (e.g., duplicate reactions, permission requirements, idempotency) or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, focused sentence with no extraneous information. Efficiently communicates the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple mutation action with no annotations or output schema, the description is adequate but could benefit from mentioning prerequisites or typical effects (e.g., if the comment exists in Metabase).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for 'id' and 'emoji', so the description adds minimal value beyond the schema. Schema coverage is considered present, but the description itself does not elaborate further.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add'), the resource ('emoji reaction to a comment'), and the context ('in Metabase'). It distinguishes from siblings like 'add_dashboard_card' or 'create_comment'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, such as whether the comment must exist first or if there are any restrictions on emoji usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description only states the action; it does not disclose behavioral traits like visibility, duplicates, limits, or permission requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no redundancy, front-loaded with action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Minimal description for a simple create operation. Lacks return value details, error conditions, or ordering context. At least covers basic purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema provides full parameter descriptions (id, model). The tool description does not add new meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb ('create'), resource ('bookmark'), and scope ('card, dashboard, or collection'). Distinguishes from siblings like 'delete_bookmark' and 'reorder_bookmarks'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Does not mention prerequisites, limitations, or exclusion cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states 'create' without addressing mutation effects, name uniqueness, return value, or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no redundancy. Efficient and front-loaded with the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations or output schema, the description is minimal. It fails to explain what a native query snippet is or its lifecycle (e.g., reusable SQL pieces stored in collections).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no extra meaning beyond the input schema, which already includes descriptive parameter names and descriptions for each field. Baseline 3 applies due to high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Create') and resource ('native query snippet in Metabase'), clearly distinguishing it from sibling tools like update_snippet, archive_snippet, and list_snippets.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_card for SQL queries) or prerequisites (e.g., collection must exist).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must convey behavioral traits. It only states 'delete' without mentioning permissions, irreversibility, cascading effects, or what happens upon deletion. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one clear, concise sentence with no unnecessary words. Front-loaded with purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation, the description covers the basic purpose but lacks details on return values, side effects, or permissions. No output schema exists to fill gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'id' is described in the schema as 'Card ID to delete'. The tool description adds no additional meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Delete a card (saved question) from Metabase' clearly states the action (delete) and the resource (card/saved question), distinguishing it from sibling tools like delete_dashboard or delete_action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, such as when to use delete_card vs delete_dashboard or other deletion tools. Missing context on prerequisites or consequences.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It only states the action but fails to disclose behavioral traits like whether the operation is idempotent, what happens if the link doesn't exist, or if specific authorization is required. For a delete operation, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no unnecessary words. It is front-loaded and directly states the purpose. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description covers the basic purpose but omits behavioral context and usage guidance. It is minimally viable but lacks completeness for an agent to use it confidently without making assumptions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, meaning the description must add meaning. It does explain that dashboard_id is the 'Dashboard ID to remove public link from', but it doesn't describe the wrapper object 'input' or clarify its role. The description adds some context beyond the schema, but not enough to fully compensate for the lack of schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete) and resource (public sharing link from a dashboard in Metabase). It distinguishes from sibling tools like create_dashboard_public_link and delete_card_public_link by specifying the exact resource type and parent object.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. It does not mention prerequisites such as the existence of the link, user permissions, or idempotency. The description leaves the agent to infer usage solely from the tool's name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only says 'Delete' without disclosing any side effects, irreversibility, required permissions, or impact on related data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that communicates the essential purpose without any extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation, the description is adequate in purpose but lacks behavioral context and usage guidelines. Given no output schema and no annotations, more detail on consequences would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add meaning beyond the input schema. Although the schema itself describes the 'id' parameter, the tool description adds no additional context, leaving the agent to rely solely on the schema. Schema coverage is 0% in context signals but the schema has parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete'), the resource ('model index'), and the identifier ('by ID'). It directly addresses the tool's purpose and distinguishes it from siblings like 'create_model_index' or 'get_model_index'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no prerequisites, and no mention of conditions under which deletion is appropriate or safe.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should disclose behavioral traits. It does not mention side effects, reversibility, permission requirements, or impact on existing persisted models.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence) and front-loaded. However, it could include a bit more context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (no params, no output schema), the description is minimally adequate but fails to provide complete context about what 'disabling' entails, such as whether it is reversible or what happens to scheduled persistence.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. According to guidelines, baseline is 4 for zero-parameter tools. Description adds no parameter info, but none is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (disable), resource (model persistence), and scope (globally). It effectively distinguishes from the sibling tool 'enable_model_persistence'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus enabling model persistence, or any prerequisites or conditions. The description lacks usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. The tool can execute arbitrary SQL, including destructive statements (DELETE, UPDATE, INSERT), but the description gives no warning about potential side effects, permissions required, or whether results are returned. For a query execution tool, this is a significant omission.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no unnecessary words. The first sentence states the core function, and the second sentence provides the key usage distinction. It is front-loaded and each sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that the tool takes a nested input object and has no output schema, the description should explain what the tool returns (e.g., query results, status, error handling). It does not. The description is incomplete for an agent to fully understand the tool's behavior and output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the input schema includes descriptions for parameters like 'type' and 'native.query', the overall description adds little beyond echoing the schema. It does not explain the structure of the 'query' object or the 'template-tags' object, which are complex. With 0% schema description coverage (meaning the description does not compensate for missing schema explanations), the description falls short.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it executes MBQL or native SQL queries against a database. It clearly distinguishes between the two query types, which sets it apart from sibling tools like execute_card or run_dashcard_query that operate on specific entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use each query type: 'For MBQL queries, use type="query" and provide query object. For native SQL, use type="native" and provide native.query string.' It doesn't mention when to use this tool versus alternatives like execute_card, but within its scope it is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only adds that 'root' is supported for the root collection, but omits any mention of permissions, authentication needs, rate limits, or what happens if the collection does not exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence of 14 words with no redundancy. Every word is necessary and provides clear, direct information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with one parameter and no output schema, the description explains the input (ID with 'root' support) but fails to describe the output (e.g., returns a collection object) or any other contextual details like whether nested items are included. It is minimally complete but could be improved.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema's parameter description already explains the 'id' parameter accepts integer or 'root'. The description reiterates the 'root' support without adding new meaning. With schema description coverage effectively present, the description offers no additional semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a single collection by ID from Metabase, using the verb 'Get' and specifying the resource. It distinguishes itself from sibling tools like get_root_collection or get_collection_items by focusing on a single collection retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool over alternatives such as get_collection_items or get_collection_tree. The description lacks any context on prerequisites, limitations, or when this tool is the best choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full burden. It only states it 'gets' data, implying a safe read, but does not disclose any behavioral traits (e.g., auth requirements, rate limits, or what happens if the database does not exist). Minimal information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no unnecessary words or redundancies. It front-loads the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is minimal. It covers the basic purpose but lacks details on return format, prerequisites, or edge cases. For a simple get tool with one required parameter, it is adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add any parameter details beyond the input schema, which already provides descriptions for 'id' and 'include_editable_data_model'. Since schema coverage is effectively 100% (both parameters have descriptions in the schema), baseline 3 applies; the description adds no extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool retrieves all ID-type fields for a database in Metabase. It uses a specific verb ('get') and resource ('ID-type fields for a database'), and distinguishes from sibling tools like 'get_database_fields' which likely return all fields.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_database_fields' or 'get_field'. No context on prerequisites or exclusions. The description is a single sentence with no usage hints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only states the basic function without disclosing important behavioral traits like permissions, what 'related' means, or side effects. Minimal transparency beyond purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence of 11 words that is front-loaded and contains no unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks details about the return format, pagination, or what constitutes 'related entities'. Given the complexity of having many sibling tools and no output schema, this is insufficient for an agent to fully understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input parameter 'id' is nested and described in the schema as 'Field ID', but the description adds no additional meaning or context about the parameter's role or structure. With 0% schema description coverage, the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it retrieves related entities (tables, fields) for a given field, distinguishing it from sibling tools like get_field (single field) and get_field_summary (summary).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives such as get_field_table_ids or get_field_remapping. Usage is implied but not clarified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description mentions 'cached' values, indicating a read operation with potential staleness. However, no elaboration on cache behavior (e.g., what happens when cache is empty) or any other behavioral traits. Without annotations, more detail would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, 9 words. No redundancy, front-loaded verb. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations. The description omits return format, limitations (e.g., caching behavior), and does not guide the agent on error cases. For a tool with many siblings, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% parameter description coverage at the top level. The description does not add any meaning beyond the schema's 'Field ID' for the nested id. With low coverage, the description should compensate but fails to do so.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states action (Get) and resource (cached distinct values for a field) from Metabase. Specifically distinguishes itself from other get_* tools by focusing on cached distinct values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs siblings like get_field or search_field_values. Missing prerequisites or when-not-to-use scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description only states the operation without detailing side effects, permissions, idempotency, or error handling (e.g., what happens if key not found). For a simple get, minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no redundancy; front-loaded with actionable verb and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get tool with one parameter and no output schema, the description is adequate but could benefit from output format hints or error handling notes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description should compensate. It adds 'by key' but doesn't explain the key's format or source. The nested parameter structure is implied but not clarified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('specific GeoJSON file by key from Metabase'), distinguishing it from siblings like list_geojson.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., list_geojson) or prerequisites. The description does not specify context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fails to disclose behavioral traits such as read-only nature, permissions, or error responses. It only states the basic function without additional context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that is front-loaded and contains no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple getter, the description is minimally adequate but lacks details on return values, errors, or any behavioral traits. Without an output schema, more context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the parameter 'id' as 'Model index ID'. The tool description adds no further meaning beyond what the schema provides, but schema coverage is sufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('a specific model index by ID') in the context of Metabase. It distinguishes from sibling tools like create_model_index and delete_model_index.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other getters, no prerequisites or context provided. The description does not help the agent decide when to invoke this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description should disclose behavior. It only states a simple get operation, omitting aspects like authentication requirements, error handling (e.g., invalid ID), or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single sentence with no wasted words. It is front-loaded with the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple ID-based retrieval, the description is minimally adequate. However, missing output schema and annotations leave gaps about response structure and behavior, but complexity is low.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% description coverage for the single parameter 'id' with 'Notification ID'. Description adds no extra meaning beyond the schema, meeting the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'get', resource 'notification', and retrieval method 'by ID'. It is specific and distinguishes from siblings like 'list_notifications' and 'send_notification'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Siblings like 'list_notifications' exist for listing all notifications, but no differentiation is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure, but it only states the core function. It omits critical details: whether this is a read-only operation, what authorization is required, whether it returns permissions for the current user or all users, and any rate limits or performance implications. The agent cannot infer side-effect-free behavior without explicit mention.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately conveys the tool's purpose. Every word is necessary; there is no redundancy or fluff. This structure efficiently communicates the core function without overwhelming the agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple fetch operation with one parameter, the description is minimally adequate but incomplete. It fails to describe the output format or structure (no output schema provided) and omits usage guidance and behavioral context. A more complete description would explain what kind of permissions are returned and any relationships to other entities, but as-is it leaves significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'db_id' is already described in the input schema as 'Database ID'. The description adds no semantic value beyond what the schema provides. While the schema coverage effectively covers the parameter, the description misses an opportunity to specify how to obtain the database ID or any constraints (e.g., 'ID must correspond to an existing database in Metabase'). Score is baseline 3 due to adequate schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Get') and the resource ('data permissions for a specific database') with a specific scope (by database ID). This verb+resource+scope pattern effectively distinguishes it from sibling tools like 'get_data_permissions' or 'get_permissions_for_group', leaving no ambiguity about its target.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'get_data_permissions' (which might return all permissions) or 'get_permissions_for_group' (which filters by group). There is no mention of prerequisites, context, or exclusions, leaving the agent without decision support for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states the action and resource, omitting details such as whether the operation is read-only, has any side effects, or performance implications. The description adds no value beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise and front-loaded. It wastes no words, though slightly more detail could be added without loss of conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a simple getter with no output schema and one empty input, the description is minimally adequate. However, it fails to specify return format or behavior when no candidates exist, leaving gaps in context for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% coverage (parameter 'input' is an empty object with no properties). The description does not explain what this parameter is for or how to use it, leaving the agent without guidance despite the single required parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'dashboard question candidates', and the scope 'from the root collection'. It distinguishes itself from the sibling 'get_collection_dashboard_question_candidates' which operates on a specific collection, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving candidates from the root collection, but does not explicitly state when to prefer this over 'get_collection_dashboard_question_candidates' or other alternatives. No exclusions or prerequisites are mentioned, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the burden. It states a read operation, implying non-destructive behavior, but does not disclose error handling, permissions, or side effects. Minimal adequate disclosure for a simple get.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, 8 words, front-loaded with tool purpose. No wasted words or unnecessary details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description should provide more context about what a segment is, return data structure, or usage notes. It is incomplete for an agent unfamiliar with Metabase.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not add any meaning to the parameter beyond what the schema provides (the schema already describes 'id' as 'Segment ID'). Schema description coverage is 0% from the tool description, and it fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool retrieves a single segment by ID, with specific verb 'Get' and resource 'segment'. It distinguishes from sibling tools like list_segments, create_segment, delete_segment, and update_segment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not mention when to use this tool over alternatives like list_segments for multiple segments, or update_segment for modifications. Implicit usage only.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral traits such as read-only nature, error conditions, or side effects. The agent is left to assume it is a safe read operation without explicit confirmation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that efficiently conveys the tool's purpose without superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-ID operation, the description is adequate but lacks details about return values, error handling, or any additional context that would help the agent use it effectively without external knowledge.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides a description for the 'id' parameter ('ID of the timeline event'), but the overall input object lacks a description. The description reiterates 'by ID' but adds no additional semantics beyond what the schema offers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'timeline event by ID' in Metabase, distinguishing it from sibling tools like create, delete, and update.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites or exclusions, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses destructive nature and irreversibility, which is critical. With no annotations, description carries full burden. However, it omits potential cascading effects (e.g., deletion of nested items) and authorization requirements, so it's only partially transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: a single sentence with 10 words. No redundancy or extraneous information. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the destructive nature and lack of output schema, the description covers the core action and irreversibility. However, it misses important context like whether deletion cascades to sub-collections or items, and it does not specify the difference from the soft-delete sibling. More detail would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'id' has a description in the schema ('Collection ID to permanently delete'), so schema coverage is high. The tool description does not add additional meaning beyond what the schema provides, meeting baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Permanently delete a collection' with specific verb and resource. The 'cannot be undone' adds permanence. However, it does not explicitly differentiate from sibling 'delete_collection', which might be a soft delete, leaving ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives. The sibling list includes 'delete_collection', but no comparison or when-not-to-use advice is provided. The description implies irreversible action, but lacks explicit usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits like read-only nature, rate limits, or potential performance impact. For a list operation, safety is implied but not stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no unnecessary words. Perfectly concise for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and low complexity, the description is basic but adequate. However, it lacks details about what glossary entries contain or prerequisites for using the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the schema provides full coverage. The description adds no additional meaning beyond what the schema states, meeting the baseline expectation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'glossary entries in Metabase', which is specific and directly distinguishes it from sibling tools like get_glossary_entry or create_glossary_entry.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, such as listing specific entries or filtering. The description does not mention any prerequisites or context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavioral traits. It states that calling the tool triggers a sync, but does not mention idempotency, side effects, rate limits, or whether the sync is immediate. The description gives basic behavioral info but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the primary action. No unnecessary words. Each sentence adds distinct information: first states what it does, second when it's used. Perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has three parameters and no output schema, the description is too brief. It omits details about the synchronous parameter (effect of true/false), the table_name parameter (when to use), and return behavior (likely a success response). The description is incomplete for an agent to use correctly without external knowledge.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the tool description adds no value beyond the input schema. The description does not explain the purpose of any parameter (id, table_name, synchronous). With low coverage, the description fails to compensate, leaving the agent without guidance on how to set parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Notify Metabase that a database has changed and trigger a sync by database ID.' It specifies the verb (notify/trigger), resource (database sync), and mechanism (by database ID). It also distinguishes from siblings like 'notify_database_sync_by_name' and 'notify_new_database_table' by emphasizing the ID parameter.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context: 'Used by external systems to signal that a DB schema or data has changed.' However, it does not explicitly state when to use this tool versus alternatives (e.g., 'sync_database' or 'notify_database_sync_by_name') or when not to use it. The usage guidance is implied but not precise.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It only states it searches parameters, but does not disclose behavioral traits such as authentication requirements, rate limits, or whether it returns only matching values or all values.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that is concise and front-loaded. Every word contributes to understanding the tool's purpose without unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without an output schema, the description does not explain return values or pagination. Given the simplicity of the tool and the presence of sibling search tools, additional context about scope (public vs internal) would be helpful but is not strictly missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover all parameters (uuid, param_key, search_string) with clear explanations. The tool description adds no further meaning beyond what the schema already provides, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Search'), resource ('parameter values'), and context ('publicly shared dashboard from Metabase'). It distinguishes from sibling tools like 'search_card_param_values' by specifying 'public dashboard'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Sibling tools like 'search_dashboard_param_values' and 'search_public_dashboard_param_values' exist, but the description does not clarify when to choose this one.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only says 'Update an existing user'. It fails to disclose whether updates are partial or full replacement, required permissions, or any side effects. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded and concise. It efficiently communicates the core purpose without waste, though it could benefit from a bit more detail without sacrificing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, and the presence of many optional fields, the description is too minimal. It does not explain return values, partial update behavior, or error conditions, leaving significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already contains detailed descriptions for each field (email format, locale, etc.). The tool description adds no additional meaning beyond what is in the schema, so the baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (update), resource (existing user), and system (Metabase). It effectively distinguishes from create_user (which creates new users) and get_user (which reads user data).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by stating 'Update an existing user', but it does not explicitly provide when to use this tool versus alternatives like create_user or delete_user, nor does it mention prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether the tool is read-only, modifies state, or requires authentication. The single sentence lacks details on side effects or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It is concise and immediately communicates the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the basic purpose but lacks information on return values, error handling, or prerequisites. Given the tool's simplicity and the absence of an output schema, the description is minimally adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for the parameters (engine and details), so the description adds no new meaning. Baseline 3 is appropriate given the schema's coverage of parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool validates a database connection configuration before creation, specifying the verb 'validate' and resource. It implies a pre-step to create_database, but does not explicitly distinguish from other tools like test_channel.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says 'before creating it in Metabase', giving clear context for when to use this tool. However, it does not provide explicit when-not-to-use guidance or mention alternatives like test_channel.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description only mentions admin requirement. Lacks details on side effects, URL validity, or whether a notification is sent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words, but could incorporate more useful information without excessive length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is adequate but lacks return type, prerequisites, and behavioral details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter 'id' is well-described in the schema; description's mention of 'for a user' adds no further meaning. No other parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states action (generate), resource (password reset URL), and scope (admin only). Distinguishes from siblings like 'create_user' and 'update_user_password'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Specifies 'admin only' as a key condition, but does not elaborate on when to use this tool versus alternatives or provide exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states 'Get a single card', implying a read operation. It does not disclose error behavior, authentication needs, or other traits. For a simple retrieval, this is adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. All essential elements (verb, resource, qualifier) are present and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get operation with one parameter, the description covers the basic action. However, it omits details about the return value (the full card object) and error handling. Given the presence of many sibling tools, slightly more context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The one parameter 'id' has a schema description of 'Card ID', which the tool description only echoes as 'by ID'. With 0% schema description coverage per context, the description should compensate but does not add meaningful semantics beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Get), resource (card/saved question), and method (by ID). It effectively distinguishes this tool from siblings like list_cards and get_card_* variants by specifying it retrieves a single card by its unique ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as list_cards or get_card_metadata. There is no mention of prerequisites or conditions under which this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description lacks behavioral details like what happens if no migration exists, or the structure of the status. It only states 'get status'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise at one sentence, but could be slightly more informative without becoming verbose. Still, it is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (no parameters, no output schema), the description is minimally adequate but leaves out potential details about return format or prerequisites.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so the schema coverage is 100%. The description does not need to add parameter details, and the baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'current cloud migration status', distinguishing it from sibling tools like 'initiate_cloud_migration' and 'cancel_cloud_migration' which are actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool, such as checking status before initiating migration or polling during migration. No comparison to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It fails to explicitly state that this is a read-only operation, safe to call, or whether it requires any permissions. The description merely restates the purpose without addressing side effects, rate limits, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is exceptionally concise—a single sentence that conveys the essential purpose and a key usage detail. Every word earns its place with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core functionality, item types, and root collection support. While it omits details on pagination behavior (though limit/offset are in schema) and error handling, it is sufficiently complete for a simple list retrieval tool given the schema covers parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides full descriptions for all parameters (id, limit, models, offset), so the description adds little beyond reinforcing the special 'root' value for id. Baseline 3 is appropriate as the schema coverage is high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action (Get items) and resource (within a collection). It also specifies the supported content types (cards, dashboards, etc.) and highlights the special 'root' value for the root collection, which distinguishes it from siblings like get_root_collection_items.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the many sibling tools such as get_collection_tree, get_collection_permissions, or get_root_collection_items. The description does not specify prerequisites, alternatives, or when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does not disclose any behavioral traits beyond the name, such as read-only nature, potential authorization requirements, or rate limits. For a retrieval operation, it is minimally transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no unnecessary words. It is front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with one parameter, the description is mostly complete. However, it lacks guidance on expected behavior (e.g., what happens if dashboard not found) and response format, though no output schema exists.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides a description for the 'id' parameter ('Dashboard ID'), so the description adds no new semantic value. Schema coverage is effectively high (the parameter is documented), resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'a single dashboard', and the method 'by ID'. It effectively distinguishes from sibling tools like list_dashboards or search_dashboards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as get_dashboard_metadata or list_dashboards. There is no mention of prerequisites or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. The word 'Get' implies a read-only operation, but the description does not explicitly state non-destructiveness, required permissions, or any side effects. For a simple lookup, this is minimal but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately communicates the tool's core function. It is front-loaded with no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description covers the basic purpose. However, it lacks information about the return format (e.g., array of integers) and any constraints on input size, making it somewhat incomplete for agent reliance.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. The tool description ('Get unique Table IDs for a list of Field IDs') merely restates the schema's parameter description ('List of Field IDs to resolve Table IDs for') without adding new details like format, constraints, or examples. It does not effectively compensate for the missing schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the specific resource ('unique Table IDs for a list of Field IDs'). It is precise and distinguishes itself from sibling tools like get_field or get_table by specifying the mapping from field IDs to table IDs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like get_field or get_table. The description does not mention prerequisites, limitations, or reasons to choose this tool over others (e.g., batching instead of individual lookups).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states the action. It does not disclose safety (read-only), pagination, or return format, which is insufficient for a list operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is efficient and front-loaded, but could benefit from more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and simple list function, the description is minimally adequate but lacks explanation of what persisted models are and result interpretation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. The description does not need to add parameter info; baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (list), resource (persisted models), and scope (in Metabase), distinguishing it from sibling tools like list_cards or list_measures.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_persisted_model or list_model_indexes. There is no mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist. The description only says 'Update', implying mutation, but fails to disclose permissions, side effects, or return behavior. The version hint (v0.49+) adds minor context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no wasted words. It is concise but arguably too brief for the complexity of the tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the basic update action but lacks details on return values, prerequisites, or side effects. Given no output schema, more context could be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high (all parameters have descriptions), so baseline is 3. The description adds minimal value by mentioning 'name or position', but does not explain required fields (dashboard_id, tab_id) or the nested structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool updates a dashboard tab's name or position (specific verb and resource). It implicitly distinguishes from sibling tools like add_dashboard_tab (add) and remove_dashboard_tab (remove).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage via purpose but provides no explicit when-to-use, when-not-to-use, or alternatives. Sibling names give context, but no guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full burden. It states 'temporarily adjust' implying the change is not permanent, but does not disclose what happens when the duration expires, whether authorization is needed, or that it creates an entity (as suggested by the sibling delete_log_adjustment).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that conveys the core purpose without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool creates a temporary adjustment but no output schema is provided. The description does not mention return values, side effects, or what happens if a duplicate adjustment is created. Given the moderate complexity, more detail is needed for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description should compensate. It mentions 'log level' and 'logger namespace' but omits the required duration_ms parameter. The description adds limited value over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('adjust'), the resource ('log level for a specific logger namespace'), and the temporary nature. It distinguishes from siblings like delete_log_adjustment (delete) and list_log_presets (list).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates temporary use but does not explicitly state when to use this tool versus alternatives (e.g., for permanent changes, or to view current logs). No exclusions or alternative tools are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a destructive operation ('Remove'), but provides no details on side effects, required permissions, or reversibility. Without annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words, front-loading the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation with no parameters and no output schema, the description is adequate but lacks context about the impact or any confirmation steps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With no parameters, the description adds meaning beyond the empty schema by stating the tool's purpose, which is appropriate for a zero-param tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the verb 'Remove' and the resource 'query caching configuration', distinguishing it from sibling tools like 'get_cache_config' and 'update_cache_config'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, nor any prerequisites or conditions for deletion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It states a destructive action but does not disclose behavioral traits like reversibility, immediate effect on logging, or whether it requires special permissions. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, and to the point. Somewhat brief, but efficient given the tool's simplicity. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and no annotations, the description covers the basic action adequately. However, it could be enhanced with a note about the scope (e.g., 'user's adjustments' or 'system-wide') to improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is effectively 100%. Description adds no parameter info, but that is acceptable as there are none. Baseline for 0 parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the specific verb 'Remove' and the resource 'all temporary log level adjustments' in Metabase. It distinguishes from siblings like 'create_log_adjustment' and other delete operations that target different entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives. There is no mention of prerequisites, effects, or when not to use it. For a simple 'delete all' tool, some context about typical use cases or cautions would help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description does not disclose what data is returned (e.g., list of events, fields), permissions required, or any limits (e.g., date range).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with purpose, no extraneous words. Efficiently conveys the core function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple read operation, but missing details like what the login history contains (e.g., timestamps, IPs) and whether any filters apply. Minimal given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100% by default. Description adds no parameter info, but this is acceptable with zero parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action 'Get' and the resource 'current user login history', distinguishing it from sibling tools like get_current_user and get_logs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, such as whether it provides timestamps or IP addresses, or when to prefer get_logs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states what the tool does, without mentioning any behavior like read-only nature, authentication requirements, or what happens if no dashboard has been viewed. Minimal value added beyond the tool name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that front-loads the verb 'Get'. Every word is necessary and there is no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and no output schema, the description is minimal. It does not describe what the returned dashboard object contains or handle edge cases. It is adequate but could be more helpful by specifying return structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are 0 parameters, so the schema coverage is 100%. The description adds no parameter details, but none are needed. Baseline 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'most recently viewed dashboard', making it distinct from sibling tools like 'get_dashboard' which require an ID. The purpose is unambiguous and specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives. It does not mention that it returns only one dashboard, or how it compares to other dashboard retrieval tools like 'get_dashboard' or 'list_dashboards'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks details about side effects, authentication needs, rate limits, or return format, which is minimal for a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single concise sentence with no redundancy, efficiently conveying the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple getter without parameters or output schema, the description is adequate but omits details about what information is returned, which could be improved.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters and 100% schema coverage, the baseline is 4; the description adds no further parameter information, which is acceptable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get information') and resource ('configured Slack app in Metabase'), clearly distinguishing it from sibling tools like 'get_channel' or 'get_slack_manifest'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives; no context about prerequisites or exclusions is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only says 'get list', which is minimal. It does not disclose pagination, ordering, read-only nature, or any limits, leaving behavioral traits largely unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is efficient and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool, the description provides the essential purpose and parameter. However, it lacks details on return format, pagination, or any ordering, which would be helpful for an agent without an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the model_id parameter as 'Filter actions by model (card) ID'. The description restates this without adding new semantic meaning (e.g., behavior when omitted). Since schema coverage is high, a baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a list of actions in Metabase with an optional filter by model ID. This is specific and distinguishes it from sibling tools like get_action (single action) and other list tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (get list vs get single action) but does not explicitly state when to use this tool over alternatives like get_action, nor does it mention prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description should disclose behavioral traits such as read-only nature, pagination, or limits. It only states 'List all alerts' without any additional context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no parameters and no output schema, the description is minimally adequate. However, it could mention the output format or that it returns a list of alert objects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has an empty object for 'input', meaning no effective parameters. The description adds no parameter info, but there are none to explain. Schema coverage is irrelevant here.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (list) and the resource (all alerts in Metabase). It distinguishes from the sibling tool 'get_alert' which retrieves a single alert.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_alert' or any filtering capabilities. No mention of prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should compensate. It only states the tool lists embeddable cards and is admin-only, but lacks details on output format, pagination, or any side effects. For a read operation, minimal transparency is acceptable but falls short without annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently conveys the tool's purpose and a key constraint (admin only). No redundant words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple listing tool with no output schema, the description is adequate but lacks details about the return format or how to interpret results. It does not differentiate from sibling tools like 'list_cards' beyond 'embeddable'. More context on what 'embeddable' means would help.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one required parameter ('input' object) with no properties, effectively no parameters. With zero parameters, the baseline is 4, and the description adds no parameter information, which is acceptable since there are no meaningful parameters to describe.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all cards available for embedding, with the specific scope of 'admin only'. It distinguishes from sibling tools like 'list_cards' by focusing on embeddable cards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions 'admin only' as a condition but provides no guidance on when to use this tool versus alternatives like 'list_cards' or search tools. No when-not-to-use or alternative suggestions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description must bear the full burden of behavioral disclosure. It only states the listing action but does not mention read-only nature, authentication needs, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no wasted words. It is front-loaded and efficiently communicates the tool's functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and no output schema, the description is adequate but minimal. It explains the core action but lacks detail about return format or context for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so the baseline is 4. The description adds no extra parameter info, but none is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'list' and the specific resource 'custom GeoJSON files' with scope 'available in Metabase'. It uniquely identifies the tool among many sibling list tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, exclusions, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description does little to reveal behavioral traits beyond a basic read operation. It fails to mention pagination, sorting, or permission constraints, leaving the agent with incomplete understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence efficiently communicates the tool's purpose without unnecessary words. Every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list with no parameters, the description is adequate but lacks details on the return format (e.g., fields returned). It could be more complete for agents unfamiliar with Metabase.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters, so the description adds no parameter-specific meaning. With 0 parameters and 100% schema coverage, the baseline of 4 is appropriate as the description correctly conveys the scope.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List all permission groups in Metabase', specifying the verb and resource, and it distinguishes from sibling tools like 'get_permission_group' or other list tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., 'get_permission_group' for a single group). The description does not mention any context, preconditions, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It only says 'Store', which implies mutation, but does not disclose whether it overwrites existing keys, requires authentication, or has any side effects. More details on idempotency or permissions would be needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 10 words with no redundancy. It is front-loaded and efficiently conveys the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and lack of output schema, the description is adequate but incomplete. It does not specify return values, overwrite behavior, or whether the storage is persistent. More context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions 'namespace and key' which aligns with the schema, but does not explain the 'value' parameter beyond what the schema already provides (any JSON-serializable value). Since schema coverage is 0% at the top-level param, the description partially compensates but is insufficient for full clarity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Store), the resource (per-user key-value preference), and the scoping (by namespace and key). It effectively distinguishes from sibling tools like get_user_key_value and list_user_namespace_values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies a write operation but provides no explicit guidance on when to use this tool versus alternatives (e.g., get_user_key_value for reading, delete_user_key_value for deletion). No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Only states the requirement, not what happens when invoked (e.g., sends to a specific channel, requires configuration). Lacks behavioral details beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise single sentence. No wasted words, front-loaded with key info. Perfect for a simple 0-param tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 0 params and no output schema, the description is minimal but covers basic purpose. However, could be improved by specifying the result (e.g., 'Sends a pre-formatted bug report to the Metabase Slack channel') and any needed setup (Slack integration). Adequate but not fully informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist (input schema is empty), so schema coverage is 100%. Description adds no param info, which is acceptable per rubric baseline. No missing parameter context needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action: 'Send a bug report via Slack from Metabase'. Also notes the Pro requirement, which specifies scope. Distinguishes from siblings like submit_product_feedback by being Slack-specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Only mentions a prerequisite (Requires Metabase Pro) but no guidance on when to use this tool versus alternatives (e.g., submit_product_feedback). Missing context like 'Use when the user has Slack configured and wants to report a bug'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It reveals that the tool sends a test email but omits details such as side effects (email actually sent), failure conditions, required permissions, or what happens on success/failure. This lack of transparency limits the agent's understanding of the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that directly and succinctly communicates the tool's purpose. It contains no redundant information and is front-loaded with the key action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is fairly complete in stating the purpose. However, it lacks context about prerequisites (e.g., SMTP must be configured), expected outcomes (e.g., returns success/failure message), and how the test email is delivered. This leaves some gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not mention the parameter, but the input schema provides a clear description for the 'to' field ('Recipient email address for the test email'). Since the schema already conveys the parameter meaning, the tool description adds no additional value, yet this is acceptable given schema coverage. A 3 reflects neutral performance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: sending a test email to verify SMTP configuration in Metabase. It uses a specific verb ('Send') and resource ('SMTP configuration'), distinguishing it from sibling tools like configure_email and clear_email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (verifying SMTP configuration) but does not explicitly state when to use this tool versus alternatives, nor does it mention prerequisites or when not to use it. For example, it could benefit from noting that SMTP must be configured first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It mentions 'update' but does not describe whether settings are merged or replaced, side effects on the dashboard layout, or any prerequisites. More detail is needed for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that covers the essential purpose without any fluff. It is efficient and appropriate for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of nested parameters (parameter_mappings, visualization_settings) and no output schema, the description lacks details on return values, merging behavior, or error conditions. It is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all parameters, so the baseline is 3. The description adds only the version constraint, which is minimal additional value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'update', the resource 'dashboard card', and what can be updated (position, size, or settings). It also includes version info 'Metabase (v0.49+)' which distinguishes from potential older API versions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives like 'update_dashboard_cards' or 'add_dashboard_card'. Usage context is implied but not clearly delineated, lacking exclusions or alternative recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavioral traits. Only states 'cancel', but does not mention side effects (e.g., data loss, reversal, permissions). Lacks essential context for a destructive action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no filler. Every word earns its place, providing clear, immediate purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and a potentially destructive action, the description lacks important details about outcomes, prerequisites, and state changes. Incomplete for an agent to confidently invoke.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters; schema coverage is 100% and description adds no parameter info, which is appropriate. Baselines at 4 per rules for 0-param tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the verb 'cancel' and the resource 'cloud migration', specifying 'in-progress' scope. Distinguishes from siblings like 'initiate_cloud_migration' and 'get_cloud_migration'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
'In-progress' implies when to use, but no explicit context about prerequisites, exclusions, or alternatives. Provides minimal guidance beyond the action itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It does not mention whether the tool is read-only, if it requires specific permissions, what side effects exist (e.g., logging), or any rate limits. The description only says 'execute,' which implies a function call but lacks detail on output or mutability.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences clearly convey the purpose and usage context without any filler. The description is front-loaded with the action and resource, then the use case. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the basic purpose but lacks details about outputs, errors, or prerequisites (e.g., database connection, MBQL syntax). Given no output schema and no annotations, the description is somewhat incomplete for an execution tool, but it does convey the primary intent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter (input) with a nested query object described as 'MBQL pivot query object' in the schema, but the tool description adds no additional meaning about how to structure or use the parameter. With schema description coverage at 0% (as per context), the description does not compensate for the lack of parameter guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool executes a pivot query against a Metabase database, specifying the action (execute), the resource (pivot query), and the use case (pivot table visualizations aggregating data across multiple dimensions). This distinguishes it from generic query execution tools like execute_query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear use case: 'Use this for pivot table visualizations that aggregate data across multiple dimensions.' This tells the agent when to use it, but it does not explicitly mention when not to use it or compare it with similar sibling tools like execute_card_pivot or pivot_dashcard_query.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It mentions exporting results but does not indicate whether it is read-only, if there are limitations (e.g., result size), or if it returns a file or creates a resource. The lack of such details is a gap for safe tool usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the core purpose, and efficiently conveys the two usage modes. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description lacks information about what the export returns (e.g., binary file, URL). It also does not cover prerequisites or potential errors. While the main functionality is clear, the description is incomplete for a fully autonomous agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0% for the top-level 'input' parameter, but the tool description compensates by explaining the two query types and how to set the 'type' and related fields. However, it does not explain the 'database' or 'format' parameters, which still rely on the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool exports query results in CSV, JSON, or XLSX format, distinguishing it from sibling tools that export saved cards or dashboards. The verb 'export' and resource 'query results' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit instructions for two query modes: MBQL and native SQL, including how to structure the input fields. However, it does not explicitly state when to use this tool versus the sibling export tools for cards or dashboards, though that is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full burden for behavioral disclosure. It states that the tool retrieves data but does not mention side effects, permissions, idempotency, or other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence of 9 words with no extra verbiage. Every word contributes meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and no output schema, the description adequately conveys the tool's purpose. However, it could be more complete by specifying what kind of details are returned (e.g., version, logs, diagnostics).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and baseline is 4 per rubric. The description adds no parameter information (none exist), but also doesn't need to.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and resource ('bug reporting details and diagnostic information from Metabase'), making the purpose clear and distinguishable from sibling tools like get_logs or get_task_info.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. No context, prerequisites, or exclusions are mentioned, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description indicates read operation but doesn't disclose idempotency, safety, or auth requirements. For a simple GET, minimal risk but still lacking.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, efficient, no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple read tool with no params. Could mention what the configuration contains, but not necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in schema, so description doesn't need to add param info. Baseline 4 for 0 params.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Get', resource 'query caching configuration', and scope 'current'. Distinguishes from siblings like update_cache_config and delete_cache_config.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this vs other get tools or alternatives. Lacks context about prerequisites or scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only reveals an admin access requirement, but omits other important traits such as output format, pagination, rate limits, or authentication needs. This is insufficient for a mutation-free listing tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of six words, directly stating the tool's action, resource, and access restriction. No superfluous information is present; every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (listing, no output schema, minimal parameters), the description covers the core purpose and access constraint. However, it lacks information on the return format (e.g., list of dashboard objects) or any filtering capabilities, which would improve completeness for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a single parameter 'input' with no defined properties, and the schema description coverage is 0%. The description adds no explanation of the parameter's purpose or expected structure, leaving the agent with no useful guidance beyond the schema itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (List), resource (dashboards available for embedding), scope (all), and access restriction (admin only). It effectively distinguishes from sibling tools like list_dashboards (all dashboards) and list_embeddable_cards (cards, not dashboards).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by specifying 'admin only' and the specific purpose of listing embeddable dashboards. However, it does not explicitly mention when to use this tool versus alternatives like list_dashboards or get_embed_dashboard, leaving some room for ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should fully disclose behavioral traits. However, it only states the action; it does not mention whether admin privileges are required, if it is read-only, or any potential side effects. Minimal behavioral context is given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with precise wording. No extraneous information. It is appropriately front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The context is minimal. There is no output schema or annotation to supplement the description. For a tool returning a 'graph' of all permissions, the description lacks information about the response format, potential size, or prerequisites. It is insufficient for an agent to fully understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema is fully covered. With no parameters, the description needs no parameter details. Baseline score of 4 applies as there is no parameter information to add.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'data permissions graph', and the scope 'for all groups and databases'. It distinguishes from sibling tools like get_permissions_for_db and get_permissions_for_group by implying a comprehensive view.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies it returns the full graph, but does not explicitly state when to use this tool versus more specific alternatives (e.g., get_permissions_for_db for a single database). No exclusions or alternative mentions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It states 'Get' implying a read-only, idempotent operation, but does not disclose authentication requirements, error behavior, or side effects. Basic transparency without rich detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence of 10 words with no redundant phrasing. Every word adds value, making it extremely concise and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter 'get by ID' tool without output schema or annotations, the description is functional but lacks details on output format, authorization, or edge cases. Adequate but not fully comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
According to the context, schema description coverage is 0%. The description adds no additional meaning beyond the schema's parameter definition ('Permission group ID'). With low coverage, the description should elaborate, but it does not, leaving value unchanged.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get a single permission group by ID from Metabase' uses a clear verb 'Get', specifies the resource 'permission group', and scopes it uniquely by ID. It effectively distinguishes from siblings like 'list_permission_groups' (multiple) and mutations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for retrieving a specific group by ID but does not explicitly state when to use this over alternatives, nor any prerequisites or context. Guidelines are implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description only states the operation, lacking details on authentication, rate limits, error handling (e.g., user not found), or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, 9 words, front-loaded with verb and resource. No unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Simple tool with one parameter well-covered by schema. No output schema but return is implied as a user object. Missing explicit mention of return format, but sufficient for a basic retrieval.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has one parameter 'id' with description 'User ID'. Description adds no extra meaning; schema coverage is 100% so baseline is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states action 'Get', resource 'a single user', method 'by ID', and system 'Metabase'. Distinguishes from sibling tools like get_current_user as it requires a specific ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance. The purpose implies usage for fetching a specific user, but no mention of alternatives or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral burden. It correctly indicates a read operation ('Get list') and optional filtering. However, it does not disclose pagination behavior, rate limits, or what happens with an invalid collection_id. The description is adequate but minimal for a simple list tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 15 words, front-loaded with the verb and resource. Every word earns its place; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one optional parameter and no output schema, the description covers the essential functionality (listing cards with optional collection filter). It does not mention return format, pagination, or limits, but given the simplicity, this is acceptable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the 'collection_id' parameter as 'Filter by collection ID'. The description adds only the phrase 'optionally filtered by collection', which does not add significant meaning beyond the schema. Schema description coverage is high (100% for the only parameter), so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get list of cards (saved questions)' and the resource 'in Metabase', with optional filtering by collection. This distinguishes it from sibling tools like 'get_card' or 'list_cards_in_dashboards'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'search', 'get_card', or 'list_cards_in_dashboards'. There is no mention of prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions admin-only access, but lacks details on atomicity, error handling, limits, or side effects. The behavioral disclosure is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the essential purpose and access restriction with no fluff. It is front-loaded with the key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has nested parameters and no output schema. The description does not explain return values, error handling, or whether the operation is synchronous. Given the complexity, more context is needed for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0% (top-level 'input' has no description), and the tool description adds little beyond 'multiple settings'. The nested 'settings' parameter has a schema description with an example, but the overall parameter semantics are not enriched by the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Update), resource (Metabase settings), scope (multiple at once), and access restriction (admin only). It distinguishes from sibling tools like 'update_setting' which likely handle single settings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for batch updates and restricts to admin users, giving clear context. However, it does not explicitly mention when not to use or specify alternatives for single settings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It states the tool returns the count of all API keys, but does not disclose any side effects, authentication requirements, or response format. The description is straightforward but minimal for a simple read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One concise sentence front-loads the purpose with no waste. Perfectly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the tool is simple, without an output schema the description should specify the return format. It says 'count' but not whether it's an integer or JSON object. Additionally, given the presence of list_api_keys, a brief note on when to use count vs list would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters, so schema description coverage is 100%. The description adds nothing beyond the schema, which is acceptable as there are no parameters to document. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool counts all API keys in Metabase. The verb 'Get' and resource 'count of all API keys' are specific, and it distinguishes from siblings like list_api_keys which returns the list, not just the count.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this versus alternatives like list_api_keys. The description implies it's for getting a count, but does not provide when-not-to-use or mention alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must cover behavioral traits. It states 'delete', which implies a destructive action, but does not mention side effects (e.g., irreversibility, behavior if key not found). Adequate for a simple delete, but leaves some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no unnecessary words. Highly concise and front-loaded with the core action and target.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation with two parameters and no output schema, the description covers the essential purpose. However, it lacks details on edge cases like non-existent keys or idempotency, which would improve completeness given the absence of annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has descriptions for 'key' and 'namespace', so the schema provides basic semantics. The tool description adds no additional parameter context beyond stating 'by namespace and key'. With schema coverage effectively 100% (descriptions present), baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Delete a per-user key-value preference by namespace and key', specifying the action (delete), resource (user preference), and required identifiers. This distinguishes it from related tools like put_user_key_value.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for deleting a user preference but provides no guidance on when to use it vs alternatives or when not to use it. Given many sibling tools, more explicit context would help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It implies a read operation ('Retrieve') but does not explicitly state it is non-destructive, note any authorization requirements, or describe potential side effects. The description is minimal but adequate for a simple retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (two sentences, under 150 characters) and front-loaded with the core purpose. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the tool has zero parameters and no output schema, the description only states 'aggregated analytics data' without specifying the format or structure of the returned data. More detail would help an agent understand what to expect, but the simplicity of the tool keeps the score from being lower.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters with 100% coverage, so the description does not need to explain parameters. The baseline score of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Retrieve') and the resource ('anonymous usage statistics from Metabase'), and specifies the return value ('aggregated analytics data'). It distinguishes itself from sibling 'get_*' tools by focusing on usage statistics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or context. It simply states what it does without any when/when-not instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It states the key behavior of not executing the query, but lacks details on output format, authentication requirements, side effects, or error handling. The non-execution trait is well highlighted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action, and includes a useful clarification (non-execution) and a practical use case. Every sentence adds value with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter, no output schema, and no annotations, the description covers the basic purpose and a key behavioral trait. However, it lacks information about the return format, potential errors, or prerequisites, which would be helpful for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for the top-level parameter 'input', though the nested 'query' property has a description. The tool description adds the context that it takes an MBQL query, but does not elaborate on the structure. Given low schema coverage, the description provides necessary but minimal added meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool converts MBQL queries to native SQL without executing, using specific verbs ('convert', 'inspect', 'debug') and identifies the resource (MBQL query to native SQL). It distinguishes from execution-focused siblings like execute_query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions use cases ('inspecting... debugging') but does not explicitly state when not to use it or compare to alternatives like other conversion or execution tools. The context is implied but not fully specified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states that the tool 'gets' the manifest, implying a read operation, but provides no details about authentication requirements, rate limits, or the nature of the returned data. This is minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—one sentence with a prerequisite note. It is front-loaded with the most critical information and contains no redundant words. Every part is valuable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and no output schema, the description is brief but sufficient for a simple retrieval operation. However, it lacks context about what the manifest contains or the format of the response, which could be useful for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters, the baseline is 4. The description adds no parameter information beyond what the empty input schema provides, but there is no need for additional parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get), the resource (Slack app manifest), and the source (from Metabase). It distinguishes itself from the sibling tool 'get_slack_app_info' by specifying 'manifest', so purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly notes a prerequisite ('Requires Metabase Pro'), which helps users know when the tool is applicable. However, it does not provide guidance on when to use this tool versus the related sibling 'get_slack_app_info', nor does it specify conditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description does not disclose pagination behavior (limit/offset defaults), authentication requirements, rate limits, or whether full user objects are returned. Adequate for a read-only tool but missing some transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with verb and resource, no wasted words. Efficiently conveys purpose and filter options.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description could explain return value structure (e.g., list of user objects) and pagination behavior. It is sufficient for basic understanding but lacks details for comprehensive usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%; description mentions three filter parameters (status, query, group) but omits limit and offset. However, the input schema provides detailed descriptions for each parameter. Description adds minimal extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'List all users' with optional filters (status, search query, group). Verb and resource are specific, and it differentiates from siblings like 'get_user' (single) and 'search' (general).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage (listing users with filters) but does not explicitly state when to use this tool versus alternatives like 'get_user' or 'search'. No exclusions or when-not-to-use guidance provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. It states 'trigger a sync,' which implies a mutation side effect, but does not disclose whether the operation is idempotent, what happens if called repeatedly, or if there are any prerequisites like authentication or existing database configuration. The behavioral disclosure is minimal, leaving agents without sufficient safety context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no wasted words. The first sentence clearly states the action and key identifiers, and the second provides usage context. It is front-loaded with the core purpose and is appropriately sized for a straightforward notification tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema and no annotations. It has 4 parameters (nested object with 4 properties) and moderate complexity. The description covers the core purpose and identification method but does not explain the effect of optional parameters (table_name, synchronous) or what the response indicates (success/failure). For a notification/trigger tool, this may be adequate, but it leaves gaps for an agent deciding how to use it optimally.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions 'by engine and database name,' which corresponds to the two required parameters (engine, database_name) and adds context that they are used for identification. However, schema coverage is 0% (no parameter descriptions in the description itself), and the description does not address optional parameters (table_name, synchronous). The schema already provides basic descriptions, so the description adds some meaning but not full parameter guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Notify Metabase that a database has changed and trigger a sync by engine and database name.' It specifies the action (notify/trigger), the resource (database identified by engine and name), and distinguishes from similar tools like notify_database_sync (which requires DB ID) through the explicit phrase 'without knowing the Metabase DB ID.' This is a specific verb+resource with clear sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates usage context: 'Used by external systems to signal schema or data changes without knowing the Metabase DB ID.' This tells when to use (when DB ID is unknown) but does not explicitly state when not to use or name alternatives like notify_database_sync. However, the sibling list includes notify_database_sync, so a knowledgeable agent could infer the alternative. The guidance is clear but lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states the action and return value, but does not mention side effects, permissions required, whether the link is permanent, or any other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately conveys the tool's purpose and return type, with no extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is largely complete. It could mention the input structure, but the schema covers that. The return value is noted.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a single parameter with a description ('Action ID to create a public link for'), providing meaning. The tool description adds no additional parameter context beyond the schema, but schema coverage is high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: creating a public sharing link for an action in Metabase, and mentions the return type (UUID). It distinguishes from sibling tools like create_card_public_link or create_dashboard_public_link.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for creating a public link for an action, and the name differentiates it from other public link creation tools. However, it does not explicitly state when to use this tool vs alternatives, such as for cards or dashboards.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the read operation without disclosing potential behaviors like pagination, error handling, or authentication requirements beyond 'for the current user'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded with the action and resource, containing no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no output schema and minimal parameters, the description is sufficiently complete, though it could mention ordering or pagination limits.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no meaningful parameters, so the description does not need to add parameter details. Baseline is 4 due to zero parameters with content.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Get list' and identifies the resource 'all bookmarks for the current user in Metabase', which clearly distinguishes it from sibling tools like create_bookmark and delete_bookmark.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies context (list bookmarks for current user) but provides no explicit guidance on when to use this tool versus alternatives like list_cards or list_collections.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the superuser permission requirement but omits other behavioral details such as pagination, filtering, or side effects. With no annotations, more transparency would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded, conveying the core purpose and a critical constraint without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool, the description covers the main purpose and a constraint, but lacks explanation of the empty input parameter and does not describe the output format. Moderate completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter which is an empty object; the description does not explain its role or expected contents, leaving ambiguity even though schema coverage is 0%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies that the tool lists all dashboards with public sharing links and notes that it is superuser-only, effectively distinguishing it from siblings like list_dashboards and list_public_cards.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states a key usage condition (superuser only), which gives context, but does not explicitly tell when to use this tool versus other list tools or mention when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It explicitly states the critical destructive behavior: 'Cards not in payload are removed.' This is a key transparency point. However, it does not mention error states, permission requirements, or impact on card ordering/tabs, which would strengthen transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences, no filler, front-loaded with the purpose. Every word serves a purpose, and the critical behavioral note is included without extra text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex bulk operation with nested parameters, the description covers the essential behavioral impact (card removal). The schema details the parameters. However, the lack of output schema and absence of guidance on error handling or ordering leaves minor gaps. Still, it is largely complete given the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter-specific information beyond what is already in the input schema. The schema itself provides decent property descriptions for each field (e.g., 'id', 'col', 'row'). Since schema coverage is effectively high from the schema's own descriptions, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'update' and resource 'dashboard cards' with the scope 'bulk'. It also mentions a version constraint (v0.49+). This effectively distinguishes it from siblings like 'add_dashboard_card', 'remove_dashboard_card', and 'update_dashboard_card' by implying it handles multiple cards at once.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lacks guidance on when to use this tool versus its sibling 'update_dashboard_card' (singular). It does not state prerequisites, scenarios where removal is undesirable, or alternative approaches. The agent is left to infer usage from the bulk nature.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states it returns a list, but does not disclose any behavioral details such as pagination, ordering, or whether it returns all databases. The description is minimally transparent for a simple read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no filler words. It is front-loaded and efficiently communicates the tool's purpose. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool with no output schema, the description is adequate but lacks details about what the returned list contains. It does not mention fields or structure of the database objects, which would be helpful for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, and schema description coverage is 100%, so the description does not need to add parameter meaning. The baseline of 4 applies; no additional explanation is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get list of databases configured in Metabase' clearly states the action (list) and the resource (databases). The tool name matches, and it distinguishes itself from siblings like list_all_tables, list_database_schemas, etc. It is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving the list of databases, but it does not explicitly provide when-to-use or when-not-to-use guidance. It lacks alternatives or exclusions, which would help an agent decide between this and similar list tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'List all' suggests a read-only operation with no side effects, which is accurate. However, it does not mention any behavioral details like pagination, rate limits, or permissions, though such details are less critical for a simple list operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, short sentence that immediately conveys the tool's purpose. It is front-loaded and contains no extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 params, no output schema), the description is minimally adequate. However, it does not clarify what the returned list contains (e.g., IDs, names, full objects). A brief note on the return format would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the input schema has 100% coverage with no properties. Per calibration, 0 parameters earns a baseline of 4. The description adds no parameter information, but none is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'List all model indexes in Metabase' uses a specific verb ('List'), identifies the resource ('model indexes'), and specifies the context ('in Metabase'). It clearly distinguishes from sibling tools like 'get_model_index' (single) and 'create_model_index' (creation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for listing all indexes, but it does not explicitly state when to use it versus alternatives (e.g., 'get_model_index' for a specific index). No exclusions or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a read operation ('Get') but does not disclose side effects, authorization needs, or data scope. With zero parameters and low complexity, this is minimally adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded with the key action and purpose. While adequate, it could be more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and no annotations, the description is sufficient for a simple read operation. However, it lacks details about what exactly 'connection pool details' includes, which may limit an agent's understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no properties (0 parameters), and schema description coverage is 100% trivially. The description adds no parameter information, which is acceptable given no parameters exist. Baseline for 0 params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'database connection pool details', and the specific context 'for bug reporting in Metabase'. This distinguishes it from other get_* tools like get_bug_reporting_details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies the use case 'for bug reporting', which gives clear context for when to use this tool. However, it does not explicitly exclude other scenarios or mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description only mentions it's a list operation. It does not disclose behavioral traits such as pagination, ordering, or limits. For a read-only list, this is adequate but lacks information on the return format or any potential side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence of six words, highly concise and front-loaded with the key action and object. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with no parameters. The description covers the basic purpose. However, it does not describe the return value (e.g., structure of listed channels), which could be helpful. Given the simplicity, it's nearly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and schema coverage is 100%. The description does not need to add parameter details. It appropriately states the listing scope, which is sufficient for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'List all notification channels in Metabase' clearly states the action (list), object (all notification channels), and scope (in Metabase). It effectively distinguishes from sibling tools like 'get_channel' (specific channel) and 'create_channel' (create a channel).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives. However, it's implicit that it is for listing all channels; for a specific channel, 'get_channel' would be used. No explicit when-not or alternatives are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states what the tool does but does not disclose behavioral traits like read-only nature, performance, or lack of side effects. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and no output schema, the description is mostly complete. It could mention if it returns all fields or ordering, but for a simple list tool, it suffices.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (no parameters). The description adds no parameter-level detail, which is acceptable since none exist. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and resource ('actions with public sharing links'), clearly distinguishing this tool from the sibling 'list_actions'. It precisely defines the scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly indicates the tool's purpose and usage context (listing publicly shared actions). It implies when to use this over 'list_actions', but lacks explicit alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must cover behavioral traits. It correctly notes admin-only privilege requirement but doesn't mention side effects or output structure. Adequate for a simple read tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with all essential information. No wasted words. Front-loads the action and constraint.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is sufficient given no parameters and no output schema. It clearly states the scope and authorization. A mention of the return format would be nice but not necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so schema coverage is 100%. Baseline for 0 params is 4. Description adds nothing about parameters, which is acceptable since none exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states that it lists all settings in Metabase and notes it is admin-only. Distinguishes well from sibling 'get_setting' which retrieves a single setting.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives like 'get_setting' or 'bulk_update_settings'. The admin-only note is helpful but not enough for full usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the licensing requirement ('Requires Metabase Pro'), which is a behavioral trait. However, it does not explain what happens during refresh (e.g., token replacement, downtime, side effects). Partial transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, clear sentence front-loads the key information. No redundant words. Perfectly concise for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description covers the essential: action and requirement. It lacks detail on what 'refresh' entails operationally (e.g., return value), but given the simplicity, it is largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, and schema coverage is 100% (empty schema). The description adds no parameter information, but none is needed. Baseline for 0-parameter tools is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Refresh') and the resource ('Metabase Pro license token'), with a specific verb-noun pair. It distinguishes from sibling 'get_premium_token_status' by using 'refresh' instead of 'get'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description notes a prerequisite ('Requires Metabase Pro'), which provides some usage context. However, it does not explicitly state when to use this tool versus alternatives (e.g., when to refresh vs check status), nor any exclusions. More explicit guidance would be beneficial.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It describes a read operation ('Get') with no side effects, but does not disclose any behavioral traits such as authentication requirements, rate limits, or whether the list is cached. For a simple read tool, it is adequate but not exceptional.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, complete sentence that conveys all necessary information without unnecessary words. It is front-loaded with the key action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and no annotations, the description is fully sufficient. It explains the purpose and scope clearly, leaving no ambiguity for a simple list operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so no parameter documentation is needed. The description correctly implies no inputs are required, and the baseline for 0-param tools is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'list of users', and the specific context 'eligible to receive notifications and alerts in Metabase'. It effectively distinguishes from sibling tools like list_users by focusing on notification recipients.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly conveys usage for retrieving notification recipients but provides no explicit guidance on when to use this tool versus alternatives like list_users or search-based tools. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It indicates the access requirement but does not disclose the return format or any other behavioral traits. Minimal for a simple read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no waste. Every word is necessary and informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple status check with no parameters and no output schema, the description covers the essential purpose and prerequisite. Could briefly mention what the status includes, but it's adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. The description does not need to add parameter info. Baseline for 0 params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get the status') and the resource ('Metabase Pro license token'), and includes the prerequisite. It distinguishes from other get_* tools by its specificity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the prerequisite (Metabase Pro), providing clear context for when to use. However, it does not explicitly state when not to use or provide alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
While no annotations are provided, the description discloses the important behavioral constraint that the API does not support filtering by collection. However, it does not mention other behavioral aspects like pagination, return format, or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences: the first states the purpose, the second provides usage guidance. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description covers the purpose and a key limitation. It could mention that the result is a list of dashboard summaries, but the lack of output schema makes this a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter that is an empty object, meaning no actual parameters. The description adds no parameter details because none are needed. With 0 parameters, the baseline is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get list of all dashboards in Metabase', providing a specific verb and resource. It distinguishes itself from the sibling tool get_collection_items by noting the lack of filtering capability.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly notes when to use this tool (when you need all dashboards) and when not to (if you need collection filtering), and provides an alternative: 'use get_collection_items with models: ["dashboard"]'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![metabase-mcp MCP server](https://glama.ai/mcp/servers/takeokunn/metabase-mcp/badges/card.svg)](https://glama.ai/mcp/servers/takeokunn/metabase-mcp)

Score Badge

Copy to your README.md:

[![metabase-mcp MCP server](https://glama.ai/mcp/servers/takeokunn/metabase-mcp/badges/score.svg)](https://glama.ai/mcp/servers/takeokunn/metabase-mcp)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/takeokunn/metabase-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server