DMTicket MCP Server

Server Quality Checklist

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

Latest release: v0.1.0
Disambiguation1/5
Many tools have overlapping purposes, e.g., 'create_a_contact' and 'contact_create' both create contacts. The naming is inconsistent, making it hard to distinguish between similar operations.
Naming Consistency1/5
Tool names follow no consistent pattern, mixing 'contact_list', 'create_a_contact', 'get_details_of_a_contact', and 'contact_create' without rhyme or reason.
Tool Count1/5
With 155 tools, the server is far too large for a typical MCP tool set. This excessive granularity undermines usability and suggests many tools could be merged or parameterized.
Completeness2/5
While the server covers many entities (contacts, conversations, agents, etc.), the massive redundancy and poor organization indicate significant gaps in coherent workflow coverage.
Average 2.4/5 across 155 of 155 tools scored. Lowest: 1/5.
See the Tool Scores section below for per-tool breakdowns.
- 0 of 1 community issues answered or closed in the last 6 months
- 7 commits in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is failing
Add a LICENSE file by following GitHub's guide. Once GitHub recognizes the license, the system will automatically detect it within a few hours.
If the license does not appear after some time, you can manually trigger a new scan using the MCP server admin interface.
MCP servers without a LICENSE cannot be installed.
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?
With no annotations provided, the description carries full responsibility for behavioral traits but offers none—no indication of read-only vs. destructive, rate limits, or other side effects. It provides no transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
While very short, the description is under-specified and fails to earn its place. It omits essential information that an AI agent needs to correctly invoke the tool.
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 7 parameters, no output schema, and no annotations, the description is severely incomplete. It does not cover pagination, default filtering, or response format, leaving the agent without sufficient 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 adds no meaning beyond what the input schema provides. Schema coverage is only 57%, and the description does not clarify undocumented parameters (labels, team_id, inbox_id) or add context to existing ones.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Conversations List' is a tautology that merely restates the tool name without specifying any action (e.g., list, get) or resource scope. It fails to convey what the tool does.
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 is given on when to use this tool versus sibling tools like 'conversation_list_meta', 'conversation_filter', or 'get_details_of_a_conversation'. No context, prerequisites, 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.
Behavior1/5
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 'Create Contact', with no mention of side effects, permissions, rate limits, 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (two words), but this comes at the cost of underspecification. It fails to provide necessary information to use the tool effectively.
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 and output schema, the description should compensate with rich context. It does not explain the purpose, prerequisite conditions, or what the tool actually does beyond its name.
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 zero parameters, the input schema provides no meaning. The description adds no value beyond the tool name, failing to provide any context about what constitutes 'contact' or what properties are set.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create Contact' is a tautology that merely restates the tool name. It does not specify what kind of contact, in which system, or distinguish it from sibling tools like 'create_a_contact'.
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 is provided on when to use this tool versus alternatives such as 'create_a_contact', 'contact_update', or other contact-related tools. The description gives no 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. There is no mention of side effects, permissions, rate limits, or return behavior, which is critical for a tool with a complex nested input schema.
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 (two words), but brevity without substance is under-specification, not conciseness. It does not front-load key information; it simply wastes the available space.
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 the tool (2 parameters, one being a nested array of objects with multiple fields and enums), the description is completely inadequate. There is no output schema, and the description provides no context for the response or pagination 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 zero meaning to the parameters. Although the schema itself defines properties and enums for filter operators, the description fails to explain how these parameters should be used, the role of page, or the structure of payload.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Contact Filter' is a tautology that merely restates the tool name without specifying the verb, resource, or scope. It provides no actionable information about what the tool does or how it differs from sibling tools like contact_list, contact_search, or conversation_filter.
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 offers no guidance on when to use this tool vs alternatives. With many contact-related siblings (contact_list, contact_search, contact_create, etc.), the lack of context leaves agents without any decision support.
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?
The description lacks any behavioral details, such as whether the tool is read-only, destructive, or requires specific permissions. No annotations are provided to compensate, leaving the agent unaware of side effects 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At two words, the description is extremely concise but fails to convey necessary information. True conciseness requires completeness; this is under-specification.
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 detailed descriptions, the tool definition is nearly useless. The agent cannot determine what the filter returns, how to interpret results, or how pagination works.
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 parameters beyond what the schema provides. With 0% schema description coverage, the agent relies entirely on the schema property names and their types, which are insufficient for complex nested structures.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Conversations Filter' is a tautology that simply restates the tool name without specifying any action or output. It does not distinguish the tool from siblings like 'conversation_list' or 'contact_filter'.
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 is provided on when to use this tool versus alternatives such as 'conversation_list' or 'contact_filter'. The tool could serve multiple unclear purposes.
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. It does not explain what updating 'last seen' entails, side effects, or required permissions. The effect on the system is completely opaque.
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 but underspecified. Conciseness should provide essential clarity, not omit required information. The description lacks structure and is therefore not effective.
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 no parameters, the description should fully explain the tool's purpose and behavior. It fails to do so, leaving the agent with no actionable understanding.
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?
Despite zero parameters (baseline 4 per rule), the description fails to add meaning beyond the name. It does not explain what the tool updates or how it determines the target.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description 'Update last seen' is a tautology that restates the tool name without specifying context (e.g., whose last seen, where it applies). No verb+resource clarity distinguishes it from other update tools.
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 like update_a_contact or update_conversation. No context about prerequisites or typical triggers.
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 bears full burden. It fails to disclose any behavior: side effects, idempotency, permissions needed, or what happens on the account.
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?
While extremely concise (4 words), the brevity sacrifices clarity. It lacks necessary structure or front-loading of critical 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 zero parameters and no output schema, the description should compensate. It does not answer basic questions: what account? what category? result format? 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.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema is empty, so the description must explain how the category is specified. It does not; it only states the action without clarifying implicit parameters or requirements.
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 'Add a new category' is vague. It does not specify what kind of category (e.g., conversation category, ticket category) or which account it belongs to. Among many sibling tools with 'add_new_*' patterns, it 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 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 like add_new_custom_attribute_to_account or add_new_automation_rule_to_account. No 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description gives no behavioral details such as required permissions, side effects, or return values. With no annotations provided, this leaves the agent with no understanding of the tool's impact.
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, which is concise but under-specified. It lacks any substantive content, making it unhelpful.
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 parameter details, the description is woefully incomplete. It does not convey the tool's purpose, behavior, or prerequisites.
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?
While the schema has no parameters (100% coverage), the description adds no meaning beyond the tool name. It fails to explain what an integration hook is, leaving the purpose completely vague.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create an integration hook' is a tautology of the tool name 'create_an_integration_hook'. It does not provide any additional information about what an integration hook is or what creating it 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?
No guidance is given on when to use this tool versus alternatives like 'update_an_integrations_hook' or 'delete_an_integration_hook'. The context of usage is entirely absent.
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 full responsibility for behavioral disclosure. It fails to state whether the tool is read-only, what data it accesses, what metrics are included, or any constraints. The agent cannot infer behavior from this minimal description.
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 noun phrase with no verbs. While short, it is under-specified and fails to convey actionable information. Conciseness should not come at the cost of clarity.
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?
There is no output schema, so the description should explain what the tool returns. It does not. The tool's name suggests metrics, but without details, an agent cannot determine if it is appropriate or 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?
The input schema has no parameters, so schema coverage is 100% (empty). The baseline for 0 params is 4, but the description adds negligible meaning beyond the schema. It hints at metrics but does not explain what metrics, how they are aggregated, or what scope (e.g., account-wide vs. conversation-specific). This is insufficient for an agent to understand the tool's purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description is 'Account Conversation Metrics', which is merely a restatement of the tool name. It lacks any verb indicating what the tool does (e.g., retrieves, fetches, gets). This is a tautology and provides no clarity on the action performed.
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 gives no guidance on when to use this tool versus the numerous sibling tools that also deal with metrics or reporting (e.g., get_account_reporting_events, list_all_conversation_statistics, get_agent_conversation_metrics). There is no mention of context or alternative 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 are present, and the description lacks any behavioral details. It does not disclose what data is returned, whether it's read-only, or any other 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 extremely short (3 words) but this brevity is due to under-specification rather than conciseness. Important context is missing.
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 annotations, and the presence of many sibling reporting tools, the description is wholly incomplete. It does not enable an agent to understand the tool's purpose or 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 has zero parameters and the schema coverage is trivially 100%. However, the description fails to add meaning beyond the schema; it does not clarify what metrics are included or the scope of the data.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Agent Conversation Metrics' is a tautology that simply restates the tool name. It does not specify a verb or resource, nor does it distinguish from sibling tools like get_account_conversation_metrics or get_agent_summary_report.
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 usage guidelines are provided. The description gives no indication of when to use this tool vs. alternatives, leaving the agent without context for selection among many similar metric 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 behavioral disclosure; no mention of read-only or destructive nature, and annotations are absent, leaving the agent uninformed.
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 brief but under-specified; lacks necessary detail for the agent to understand the tool's purpose.
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 large number of sibling tools and lack of output schema, the description is entirely insufficient 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?
No parameters exist, so schema coverage is complete; however, the description adds no value beyond the schema's emptiness.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description is 'Conversation Details' which is a tautology; it does not specify what details are retrieved, nor does it distinguish from siblings like 'get_single_conversation' or 'list_all_contact_conversations'.
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; no 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and description provides zero behavioral details: no mention of auth requirements, side effects, idempotency, or what 'update' entails. The word 'update' implies mutation but lacks critical 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?
Extremely concise (two words) but grossly under-specified. Conciseness comes at the expense of any useful 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?
Tool has no parameters, no annotations, no output schema—yet description does nothing to compensate. Agent has no basis to decide usage or 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?
Input schema has 0 parameters, so baseline is 4, but description adds no meaning beyond the name. It fails to clarify what aspects of account can be updated (e.g., name, settings). A 0-param tool still needs to explain its effect.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description is a tautology—'Update account' merely restates the name 'update_account' without adding specificity. No verb-resource distinction from sibling tools like update_agent_in_account or update_conversation.
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 (e.g., get_account_details for reads, or other update tools). No context or prerequisites provided.
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 present, and the description is a single verb phrase. It does not disclose the behavior: whether the update is partial or full, if it is idempotent, what happens if the agent bot does not exist, or any side effects. The empty schema compounds the issue.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, but it is under-specified and wastes the opportunity to provide essential context. It is not concise; it is 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?
With zero parameters, no output schema, and no annotations, the description is completely inadequate. The agent has no information on how to invoke the tool or interpret results, making it nearly unusable.
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 zero parameters, yet the tool presumably requires some identifier to know which agent bot to update. The description adds no meaning beyond the schema, leaving the agent unable to determine what to provide.
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 'Update an agent bot' names the resource and action but is vague. It does not distinguish from sibling tools like create_an_account_agent_bot or delete_an_account_agent_bot, and fails to specify what aspects of the agent bot 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 Guidelines1/5
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 versus create a new agent bot. There is no context about prerequisites (e.g., the agent bot must exist) or limitations.
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 the full burden of disclosing behavioral traits, but it fails to do so. It does not indicate whether the update is partial or full, whether authentication is required, or what side effects occur.
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) with no superfluous text, but it fails to be informative. Conciseness is not helpful without adequate content.
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 potential complexity (update operation) and the absence of output schema and annotations, the description is woefully incomplete. It does not explain return values, error states, or any 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?
Although the input schema has 0 parameters (100% coverage), the description should clarify how to specify which data source to update or what fields are updated. It adds no value beyond the schema, and the lack of parameters is unusual for an update tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Update a data source' is essentially a tautology, restating the tool name without adding any specificity. It does not distinguish this tool from sibling tools like 'create_data_source' or 'test_data_source'.
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 is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or conditions for updating a data source.
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, and the description does not disclose any behavioral traits such as whether the tool reads or mutates data, authentication requirements, or side effects. The agent has no information about safety or behavior.
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 two words, which is not concise but rather under-specified. It lacks a verb and any meaningful content to guide the agent. A sentence or two would be expected.
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 single parameter and no output schema, the description provides almost no information about what the tool returns or how it behaves. In the context of many similar sibling tools, this is completely 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?
Schema description coverage is 100% for the single parameter 'id', which is described as 'ID of the contact'. The description adds no additional meaning beyond the schema, so it meets the baseline of 3 for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description is 'Contact Conversations', which is a tautology of the tool name. It does not specify a verb or action, so the agent cannot determine what the tool does (e.g., list, get details, create?). The sibling tool 'list_all_contact_conversations' suggests that tool is for listing, but this description provides no clarity.
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 is provided on when to use this tool versus alternatives. Many sibling tools deal with contacts and conversations, but no criteria for choosing this one are 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 does not disclose any behavioral traits such as read-only nature, authentication requirements, or side effects. The burden falls entirely on the description, which 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.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At two words, the description is severely under-specified. It omits critical information and cannot be considered concise; it is merely terse.
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 and no annotations, the description is completely inadequate. It does not explain what is returned, how the conversation is specified, or any other essential details for a tool with over 100 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?
There are zero parameters, so schema coverage is 100% by default. However, the description does not add meaningful context about how the conversation is implicitly identified, leaving ambiguity for the agent.
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 'List Labels' is a tautology of the tool's last two words, adding no context. It does not specify that the labels belong to a conversation, nor does it differentiate from the sibling 'list_all_labels' which likely lists all labels globally.
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 is provided on when to use this tool versus alternatives. Given sibling tools like 'list_all_labels' and 'contact_add_labels', the agent has no basis to decide which tool 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?
With no annotations, the description must disclose behavioral traits. It fails to mention side effects (e.g., changing conversation state), permissions required, reversibility, or idempotency. The agent cannot infer what 'resolving' entails.
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?
While extremely concise (3 words), the description suffers from under-specification. It does not provide enough information for effective use, making it more of a placeholder than a valuable description.
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 zero annotations, no output schema, and no parameters, the description is the sole source of context. It is completely inadequate—no details about what resolving does, when to use, or expected outcomes. The agent cannot confidently use this 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 schema coverage is 100%. The description adds no extra meaning, but there is nothing to explain. Baseline 3 is appropriate as the schema already conveys the lack of inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Resolve a conversation' is a tautology that restates the tool name without clarifying what 'resolve' means (e.g., close, mark as resolved, change status). It does not distinguish this tool from siblings like toggle_status_of_a_conversation or update_conversation.
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 is provided on when to use this tool versus alternatives. There are no prerequisites, conditions, or exclusions mentioned, 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.
Behavior1/5
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 'Update', which is vague. It does not mention side effects, permissions, or what happens to existing 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?
While short, the description is under-specified. It does not provide enough information, making it not truly concise—just 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 large number of sibling tools and the lack of output schema, the description is completely inadequate. It fails to explain what the tool does beyond the name.
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 100% (both params have descriptions). The description adds no additional 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.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Update Conversation' is a tautology of the tool name. It does not specify what aspect of the conversation is updated or provide any distinguishing details from 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 Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are given. The description does not indicate when to use this tool versus alternatives like 'toggle_status_of_a_conversation' or 'update_custom_attributes_of_a_conversation'.
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 present, so the description must disclose behavioral traits. It fails to mention that assigning may override existing assignments, ignore team_id if assignee_id is present, or any side effects. This is a critical gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extreme brevity sacrifices clarity. One word is insufficient to convey purpose or usage. This is under-specification, not 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?
The description is completely inadequate given there is no output schema and no annotations. It does not explain the return value, prerequisites, or behavioral nuances of the assignment 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?
Schema coverage is 100% with separate descriptions for each parameter. The description adds no additional semantics beyond the schema, 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.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Assign Conversation' is a tautology that merely repeats the tool name. It lacks a verb or resource specification, making it impossible to distinguish from sibling tools like update_conversation or toggle_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 usage guidelines are provided. The description does not indicate when to use this tool versus alternatives like update_conversation or list all conversation tools. The schema suggests it may be used to assign to a team or user, but context is missing.
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 full burden. It merely says 'Add Labels' without disclosing whether labels are appended or replaced, whether the operation is idempotent, or what permissions are required. The input schema does not include a conversation identifier, implying it is passed elsewhere, but this is not clarified. Behavioral traits are completely opaque.
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 (two words) but sacrifices necessary information. It is under-specified, failing to convey the tool's purpose, behavior, or usage. Conciseness should not come at the cost 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?
The tool has no output schema, no annotations, and a single parameter. The description is insufficient for an agent to understand what happens when the tool is invoked, what the target entity is, or what the result looks like. Critical context is 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?
Schema coverage is 100% as there is only one parameter, but its description is contradictory: 'Array of labels (comma-separated strings)' suggests each element is a comma-separated string, conflicting with the schema type 'array of strings'. The example shows individual labels. This adds confusion rather than clarity, offering marginal value beyond the schema.
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 'Add Labels' is vague; it does not explicitly state that labels are added to a conversation. While the tool name suggests the context (conversation), the description should clarify the resource being acted upon, especially since sibling tools like contact_add_labels exist. It is better than a tautology but lacks specificity.
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 usage guidelines are provided. There is no indication of when to use this tool versus alternatives (e.g., contact_add_labels, list_all_labels_of_a_conversation), nor any prerequisites or context. The description offers no guidance for correct selection.
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 and no description of side effects, permissions, or what happens during an update. The tool is a mutation, but no disclosure of behavior 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.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single vague sentence that fails to provide any useful information. It is underspecified, not concise in a helpful sense.
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 zero parameters, no output schema, and no annotations, the description is entirely incomplete. The agent cannot determine how 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?
Input schema is empty, yet the tool likely requires parameters (e.g., label ID, new properties). The description does not compensate for the missing schema coverage, providing no guidance on how to invoke the tool.
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?
Description merely restates the name ('Update a label') without specifying what attributes can be updated. With sibling tools like create, get, and delete, the general purpose is inferred but lacks detail.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 contact_add_labels or conversation_add_labels, which also involve labels but in different contexts. Missing 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.
Behavior1/5
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 any side effects, authentication requirements, rate limits, or the nature of the report (e.g., real-time vs historical). The description is completely silent on these aspects.
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 (5 words), which is good for brevity, but it lacks structure and critical information. It is not front-loaded with the most important details. Additionally, being in Vietnamese may cause issues for English-speaking agents.
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 no parameters and no output schema, the description should provide sufficient context about what the report contains. It does not describe the output format, granularity, or any filtering options. This is inadequate for a reporting 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 input schema has no parameters, so the description should explain what the report covers (e.g., time range, labels included). It only mentions 'label' and 'Type' without elaborating on what types exist or how labels are used. This is insufficient for an agent to understand the report's scope.
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 'Báo cáo hội thoại theo nhãn (Type)' translates to 'Conversation report by label (Type)', which vaguely indicates a report about conversations grouped by label. However, it lacks a clear verb and does not specify what action the tool performs (e.g., generate, retrieve, export). The purpose is ambiguous compared to sibling tools that have more descriptive names.
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?
There is no guidance on when to use this tool versus the many sibling reporting tools like 'get_account_reporting_events' or 'list_all_conversation_statistics'. No context about prerequisites, alternatives, or when not to use it is provided.
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 such as read-only nature, data volume, or side effects. The agent has no information about what happens when the tool is invoked.
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 but lacks structure and completeness. It is concise but does not earn its place as it omits critical 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 no output schema and no annotations, the description is severely incomplete. It fails to explain what the tool returns, how it behaves, or how it fits with 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?
There are no parameters, and schema coverage is 100% by default. However, the description 'Get Account reports' adds minimal meaning beyond the empty schema; it does not clarify what reports are returned or how they are structured.
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 'Get Account reports' is vague and does not specify that the tool returns conversation statistics. It does not distinguish from sibling tools like 'list_all_conversation_statistics_summary' or 'get_account_reporting_events'.
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 is provided on when to use this tool versus alternatives. There is no context about prerequisites, expected 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.
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 whether the operation is additive or replacive, or any side effects. The description carries the full burden but provides nothing.
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 and under-specified, essentially just repeating the name. It is not concise in a helpful way.
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 completely inadequate for a tool with 2 required parameters and no output schema. It lacks essential context about behavior, return values, and when to use it.
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% with both parameters having descriptions. The tool description adds no additional meaning beyond the schema, so baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Update Agents in Inbox' is a tautology, restating the tool name without adding any new information about what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 siblings like add_new_agent_to_inbox or delete_agent_in_inbox. The description provides no context or differentiation.
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 like permissions or side effects, but it merely states the action without any such 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 extremely short but under-specifies the tool's purpose; it fails to be informative, making it inadequate despite its brevity.
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 tool's simplicity (2 params), the description should provide enough context for correct invocation, but it does not.
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 has high coverage (100%) with descriptions for both parameters, so the description adds no additional value but does not harm correctness.
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 'Add a New Agent' is vague and does not specify that it adds an agent to an inbox, which is necessary to distinguish it from sibling tools like add_new_agent_to_account or add_new_agent_to_team.
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 is provided on when to use this tool over alternatives, such as add_new_agent_to_account or update_agents_in_inbox, 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must convey behavioral traits. It fails to mention read-only status, authentication requirements, or side effects. The minimal text gives no insight into behavior.
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 (two words) but sacrifices clarity. It does not earn its place as it omits essential information, 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?
The tool likely requires a contact identifier but the description provides no context. With no output schema, the return values are unexplained, leaving the agent without enough information 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 has no parameters (100% coverage trivially). The description adds minimal meaning by indicating the tool shows a contact, but no further semantic detail is provided.
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 'Show Contact' is vague and does not specify what is shown or how it differs from the sibling tool 'get_details_of_a_contact'. It lacks a verb-resource-object structure.
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 is provided on when to use this tool versus alternatives like 'get_details_of_a_contact' or 'contact_list'. The description offers no context or prerequisites.
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 bears full weight for disclosing behavior (e.g., read vs. write, authentication, results). It contains zero behavioral information, leaving the agent uninformed.
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 but at the cost of informativeness. It is not meaningfully concise; it omits essential details that a few more words could provide.
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 zero parameters, no output schema, and no annotations, the description fails to convey what the tool returns or how it behaves. It is completely 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.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist and schema coverage is 100%, so baseline is 3. The description adds no param info (none needed), but neither does it provide helpful context about the tool's input or output.
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?
Description is a noun phrase ('Conversation Reporting Events') that restates the tool name without adding a verb or clarifying the action. It is vague and does not distinguish from sibling tools like get_account_reporting_events.
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 provided on when or when not to use this tool, nor any alternatives mentioned. The description is entirely silent on 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, and the description gives no behavioral information (side effects, permissions, return format). The agent cannot infer any safety or operational 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 too brief (5 words) and fails to provide necessary context. It sacrifices informativeness for brevity.
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 minimal description, the tool definition is completely insufficient for an agent to understand its purpose or 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?
There are no parameters, so schema coverage is 100%, but the description does not clarify what data source is retrieved. It adds no meaning beyond the tool name.
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 'Get a data source' is vague and does not differentiate from sibling tools like list_data_sources or query_data_source. It lacks specificity about what 'get' means (e.g., get by ID vs. get current).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_data_sources or test_data_source. The agent has no context to decide which tool to invoke.
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., read-only, pagination, result limits). The description is too minimal to compensate for the missing 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?
At two words, the description is excessively terse and lacks structure. While concise, it is under-specified and fails to provide essential context that could be conveyed in a few more sentences.
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 no annotations, the description is critically incomplete. It does not explain return format, pagination, error conditions, or differentiate from similar tools like 'contact_filter'. The agent lacks enough context to use it effectively.
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 fully describes the parameter 'q' with its supported fields. The tool description adds no extra meaning beyond what the schema already provides, so it scores below the baseline due to lack of added value.
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 'Search Contacts' clearly indicates a verb and resource, but is too brief to distinguish from sibling tool 'contact_filter' which likely performs a similar function. The input schema adds clarity on search fields, but the description itself lacks specificity.
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 usage guidance is provided. There is no information about when to use this tool over alternatives like 'contact_filter' or 'contact_list', nor any conditions 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 present, and the description merely states a create action. It does not disclose permissions, scope (global vs. scoped), side effects, or return behavior beyond the bare 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?
Overly brief single sentence that provides no structure or additional information; conciseness sacrifices utility.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 presence of many sibling label-related tools, the description is incomplete. It does not clarify how this tool relates to labeling contacts or conversations, nor what the label entity 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?
Input schema has zero properties, so description carries full burden. It adds no meaning beyond the tool name, failing to explain what constitutes a label or required fields.
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?
Description is a tautology: 'Create a label' restates the tool name without specifying what kind of label or differentiating from sibling tools like contact_add_labels or conversation_add_labels.
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, no prerequisites, no exclusions. The description provides no 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?
With no annotations, the description carries the full burden. It does not mention that the tool likely requires a conversation context or what side effects occur (e.g., message creation). No 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At 4 words, it is under-specified. Conciseness should preserve information; this sacrifices clarity for brevity.
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 likely requires a conversation context and has no output schema, the description is severely incomplete. It does not explain prerequisites, return value, or how it interacts with other tools.
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 the description cannot add meaning for them. Baseline 4 for 0 parameters, though it misses opportunity to clarify no params needed.
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 'Create New Message' is vague and does not specify the resource (message in a conversation). It could be confused with sibling tool 'create_a_message', which has a nearly identical name.
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 like 'create_a_message' or 'toggle_typing_status'. 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits like read-only nature, required permissions, or side effects. It does not, leaving the agent uninformed about whether this is a safe read operation or not.
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 three words, which is under-specified for a tool that likely returns a non-trivial result. Conciseness should not come at the cost of missing critical 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 absence of output schema and annotations, the description fails to explain what 'contactable inboxes' are or what the response contains. It is insufficient 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.
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 sole parameter 'id', so the description does not need to add parameter semantics. Baseline score of 3 is appropriate as no additional value is added.
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 'Get Contactable Inboxes' essentially restates the tool name and does not distinguish it from siblings like 'get_inbox' or 'list_all_inboxes'. While the verb and resource are clear, the description adds no additional 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?
No guidance is provided on when to use this tool versus alternatives such as 'contact_inbox_creation' or 'get_inbox'. The description lacks any 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?
With no annotations, the description carries full burden but says nothing about side effects, authorization requirements, or what the creation entails. The agent cannot infer whether this tool is destructive or has 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short but not concise—it omits essential details. Every sentence should earn its place; this single sentence fails to provide enough 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?
Without parameters, output schema, or annotations, and with a minimal description, the tool is incomplete. An AI agent cannot determine how to specify the filter or what the result will be.
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 zero parameters, so schema coverage is 100% by default. The description adds no parameter information, but given no parameters exist, the baseline is 3. The lack of parameters itself is suspicious and reduces utility.
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?
Description 'Create a custom filter' is a tautology—it merely restates the tool name without adding specificity. It does not explain what a custom filter is or how it differs from similar tools like 'list_all_filters' or 'update_a_custom_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 create a filter versus using other filter-related tools. There is no mention of prerequisites, alternatives, 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description gives no behavioral details (e.g., permissions, side effects, idempotency). The agent cannot determine what happens when this tool is invoked.
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 short sentence with no wasted words, but it is severely under-specified. Conciseness should not sacrifice necessary 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?
With no parameters, no output schema, and no annotations, the description is the sole source of context. It fails to explain what an agent bot is, prerequisites, or outcomes.
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 has 0 parameters, so schema coverage is 100%. Description could add meaning about what is created (e.g., an automated bot), but it does not. Baseline 4 reduced due to lack of clarifying context.
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 'Create an Agent Bot' restates the tool name without adding specificity. It does not distinguish from sibling create tools like 'create_a_contact' or 'add_new_agent_to_account'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 create tools in the sibling list, but the description offers no 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 gives no behavioral information. It does not disclose whether the tool is read-only, destructive, requires authentication, or any side effects, leaving the agent blind.
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—a single fragment. While it is not verbose, it is under-specified and fails to convey essential information, making it more of an omission than 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 5 parameters, no output schema, no annotations, and a sibling tool, the description is woefully incomplete. It does not explain what reporting events are, return format, limits, or filtering 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 100% with descriptions for all 5 parameters. The tool description adds no extra 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.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description is a tautology of the name, stating 'Account Reporting Events' without specifying an action. It does not clarify that the tool retrieves or lists events, nor does it distinguish from the sibling 'get_conversation_reporting_events'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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. The sibling tool 'get_conversation_reporting_events' exists but is not mentioned, and there is no 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden for behavioral disclosure. It only says 'Get a contact' with no details about permissions, return format, or how the contact is identified. This is critically 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, but it is under-specified. Conciseness should not sacrifice completeness; here, the sentence adds minimal value and does not earn its place due to lack of useful 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?
Despite low complexity (no parameters, no annotations, no output schema), the description is extremely incomplete. It fails to mention how the contact is identified, what details are returned, or any prerequisites. The agent has no way to use this tool correctly based solely on the 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?
There are 0 parameters and schema description coverage is 100%, so baseline is 3. The description does not add any parameter information (as none exist), but it could have clarified how the contact is selected (e.g., by ID). It meets the baseline but does not add extra value.
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 'Get a contact' is essentially a tautology of the tool name 'get_details_of_a_contact'. It restates the action and resource without adding specificity, such as what 'details' are included or how it differs from similar siblings like 'contact_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 usage guidance is provided. The description does not indicate when to use this tool versus alternatives (e.g., contact_create, contact_update, contact_search), nor does it mention any context 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 behavioral traits are disclosed. The description does not mention that it is a read operation, any authentication requirements, or what happens if the label does not exist. Annotations are absent, so the description carries full burden but fails.
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 concise (3 words), but under-specification outweighs brevity. Every sentence should earn its place; here, it provides minimal 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 no annotations, no output schema, and limited description, the definition is incomplete. It fails to inform the agent about return values, behavior, or how to specify the label.
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 parameters, but the description does not explain how the tool identifies a label (e.g., via context or implicit ID). A baseline of 4 is reduced due to confusion about the lack of parameters.
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 'Get a label' is vague and does not clarify which label is being retrieved. The name suggests details of a single label, but no identifier is provided, making it 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 on when to use this tool versus sibling tools like 'list_all_labels' or 'create_a_label'. The description lacks context for the AI agent to choose appropriately.
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 full burden. It gives no information about read-only nature, side effects, or required 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?
Extremely concise (two words) but at the cost of completeness. The description is underspecified and provides no additional 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?
With no annotations, no output schema, and no parameters, the description completely fails to provide context. It does not explain that the tool implicitly refers to a specific contact or how to use it.
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 has zero parameters (100% coverage). The description adds no meaning beyond the schema and does not explicitly state that no parameters are needed, but the schema already documents this.
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 'List Labels' is a tautology of the tool name and does not specify that it lists labels of a contact. It fails to distinguish from sibling tools like 'list_all_labels' (global labels) or 'list_all_labels_of_a_conversation'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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. The description does not mention any prerequisites or context (e.g., requiring a contact ID).
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 whether the tool is read-only, destructive, or has side effects. The agent is left guessing about the impact of calling this 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 extremely short (two words), which is under-specification rather than conciseness. It lacks essential details and fails to 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 (many sibling tools), lack of annotations, and no output schema, the description is severely incomplete. It does not clarify return values, pagination, or any additional context needed for correct 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?
Schema description coverage is 100%, so the parameters 'after' and 'before' are well-documented in the schema. The description adds no additional meaning, but the baseline of 3 is appropriate per guidelines.
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 'Get messages' is a tautology of the tool name and provides no specificity about what kind of messages or scope. It does not distinguish from numerous sibling tools like 'list_all_conversation_messages' or 'create_a_message'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents 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, such as 'list_all_conversation_messages' for conversation-specific messages.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 carries full responsibility for behavioral disclosure. It only repeats the name, offering no details on side effects (e.g., whether it replaces or appends agents), permissions, 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short but lacks essential content. It is under-specified rather than concise; every sentence should earn its place, but this single phrase provides no substantive information beyond the tool 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 that this is a mutation tool with no output schema and no annotations, the description completely fails to explain return values, error behavior, or operational details. It is insufficient for an agent to correctly 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?
Schema coverage is 100% with one parameter described in the schema. The description adds no additional meaning beyond the schema, but since coverage is high, the baseline is 3. However, the description does not compensate for potential ambiguity between 'update' and the schema's 'added' hint.
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 'Update Agents in Team' is a generic verb+resource but fails to specify what 'update' entails (add, remove, replace). It does not distinguish from sibling tools like 'add_new_agent_to_team' or 'delete_agent_in_team', 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 Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. There is no indication of when to use this tool versus alternatives, nor any context on prerequisites or limitations.
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 behavior, but it only says 'Update Custom Attributes'. It does not explain whether attributes are merged or replaced, if the operation is destructive, what the response looks like, or any authentication or rate limit requirements.
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 at 3 words, but this is under-specification rather than purposeful conciseness. It lacks critical information needed for correct tool use.
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 (1 param with nested object), no output schema, and no annotations, the description is far from complete. It fails to explain return values, side effects, or behavior, 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?
Schema coverage is 100% for the single parameter, which already has a description and example. The description adds no additional meaning beyond what the schema provides, meeting the baseline but not exceeding it.
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 'Update Custom Attributes' merely restates the tool name without specifying that it applies to a conversation. While the name includes 'of a conversation', the description omits this context, making it a tautology that adds no new 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?
No guidance is provided on when to use this tool versus alternatives like 'update_conversation'. There is no mention of prerequisites, context, 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description fails to disclose any behavioral traits such as whether the update is destructive, if authorization is required, or what the response contains. The agent gains no insight into 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At only two words, the description is under-specified. While concise, it fails to provide necessary detail, making it unhelpful for an agent selecting the tool.
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 parameter details beyond 'id', the description is completely inadequate. It does not explain what fields can be updated, the expected response, or any prerequisites.
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, describing 'id' as 'ID of the inbox'. The description adds no additional meaning beyond the schema, so a baseline of 3 is appropriate.
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 'Update Inbox' is a tautology—it merely restates the tool name without specifying what aspects of the inbox can be updated (e.g., name, settings). It offers no distinction from sibling tools like 'get_inbox' or 'inbox_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. There is no mention of prerequisites, when not to use it, or comparison to similar tools like 'get_inbox' or 'inbox_creation'.
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 and a one-word description, the tool discloses no behavioral traits such as permissions, side effects, or whether it creates a message in a specific channel. This is a critical gap for a creation 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?
While the description is a single sentence, it sacrifices necessary information for brevity. It is under-specified rather than concisely 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 output schema, no annotations, and zero parameters, the description provides no context about what a 'message' constitutes, where it appears, or prerequisites. Compared to richer siblings, this is completely inadequate.
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?
Input schema has zero parameters, so the description cannot add parameter-level meaning beyond the name. Baseline of 4 is appropriate as schema coverage is 100% (empty) and no parameter details are needed.
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 'Create a message' states the action and resource but fails to differentiate from the sibling tool 'create_a_new_message_in_a_conversation'. It is unclear if this creates a message in a conversation or standalone, leading to 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 'create_a_new_message_in_a_conversation'. 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits, but it gives none. There is no info on side effects, permissions, return format, or pagination.
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). While it lacks content, it is structured appropriately and front-loaded. Conciseness alone is not penalized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 low complexity, the description is insufficient. It does not explain what a successful response contains or how it differs from similar tools, 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 already describes the 'id' parameter with 100% coverage. The tool description adds no extra meaning, so baseline 3 is appropriate.
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?
Description 'Get an inbox' is almost a tautology of the name, and does not specify which inbox or what aspects are returned. It fails to distinguish from sibling 'get_details_of_a_inbox'.
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 is provided on when to use this tool versus alternatives like 'list_all_inboxes' or 'get_details_of_a_inbox'. The description is completely silent on 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 does not disclose behavior beyond minimal action. No info on permissions, idempotency, or whether removal requires a specific parameter value.
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?
Description is extremely short but under-specified. It lacks necessary detail, making it insufficient 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?
Despite low complexity and full schema coverage, the description fails to explain the tool's effect, success/error behavior, or prerequisites. Incomplete for reliable 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?
Schema covers 100% of parameters with basic descriptions, but the description adds no additional meaning. It does not explain how 'add' or 'remove' maps to parameter values (e.g., passing null to remove).
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?
Description says 'Add or remove agent bot' which is vague and conflicts with the tool name 'update'. Does not clearly state that it associates an agent bot with an inbox. Among sibling tools like create_an_account_agent_bot, purpose is 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 on when to use this tool versus creating, updating, or deleting account-level agent bots. No context for when an addition vs removal 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. It only states 'Update a message', implying mutation, but fails to mention necessary permissions, idempotency, side effects, or required authentication. The agent has no insight into the tool's behavior beyond a generic 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?
At three words, the description is under-specified rather than concise. It lacks critical details and does not earn its brevity. Every sentence should add value; this one barely states the obvious.
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 zero parameters, no output schema, and no annotations, the description is severely incomplete. The agent cannot determine how to invoke the tool, what data to provide, or what the response contains. This is insufficient for a functional 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 input schema has zero parameters, which is unusual for an update operation. The description does not explain how the target message is identified (e.g., via path, conversation context) or what values can be modified. Although schema coverage is 100%, the description fails to add meaning for the parameterless 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 'Update a message' clearly indicates a write operation on a message resource, distinguishing it from siblings like create_a_message or delete_a_message. However, it lacks specificity about what aspects of a message can be updated, leaving the scope 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 create_a_message or other alternatives. The description does not mention prerequisites, context requirements (e.g., needing an existing message), or conditions for 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, and the description gives no information about side effects, authentication requirements, or any behavioral traits beyond the bare verb 'Update'.
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 phrase 'Update Contact' is concise but underspecified; it does not add sufficient value beyond the tool 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?
For an update tool, lack of parameter identifiers and output schema makes it highly incomplete. No information on which contact or fields to update.
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?
Input schema has 0 parameters, so schema coverage is 100%. Description adds nothing but baseline is set to 4 for zero-parameter tools per calibration rules.
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?
Description 'Update Contact' is nearly identical to the tool name 'contact_update', making it a tautology. It does not distinguish from sibling tool 'update_a_contact' with 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 on when to use this tool versus alternatives like 'update_a_contact' or 'contact_create'. No context or prerequisites provided.
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 such as side effects (e.g., creating an SLA policy may affect conversations), required permissions, rate limits, or irreversible actions. The description carries the full burden but provides none of this information.
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 (one phrase), but this is under-specification rather than effective conciseness. Every sentence should add value, but here the description adds no additional detail beyond what the tool name implies. It is too terse to be useful.
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 detailed schema documentation for the parameter, the description is severely incomplete. An agent cannot determine the tool's behavior, requirements, or expected input format. This is insufficient for effective tool 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% for the single parameter 'sla_policy', which is a $ref to an external schema. The description does not explain what this parameter contains, its purpose, or how to structure it. 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 states 'Tạo chính sách SLA' which translates to 'Create SLA policy', clearly indicating the verb (create) and resource (SLA policy). However, it does not differentiate from sibling tools like update_sla_policy or get_sla_policy, lacking specificity that would help an agent select this tool over 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?
No usage context is provided. The description does not specify when to use this tool versus others (e.g., update_sla_policy, delete_sla_policy), nor does it indicate prerequisites or common scenarios. The agent receives no guidance on tool selection.
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 read-only nature, side effects, or required permissions. The tool name suggests 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at five words, front-loading the purpose. However, the extreme brevity sacrifices helpful details, making it minimally adequate rather than optimally 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 annotations, output schema, and parameter explanations, the description is severely incomplete. It fails to clarify the report's content, format, 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.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters and the schema is empty with 100% coverage. The description does not add meaning beyond the schema, but baseline is 3 due to high schema coverage. No additional parameter context is needed.
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 specifies 'Get inbox-label matrix report', indicating the action and resource. However, it lacks clarity on what a 'matrix report' entails, and does not differentiate from sibling report tools like get_label_summary_report or get_inbox_summary_report.
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 usage guidelines are provided. The description does not indicate when to use this tool versus alternatives, or any prerequisites for calling 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. Description does not mention whether it returns all messages across conversations or within a conversation, nor any pagination, ordering, or 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?
Extremely concise (one sentence), but lacks necessary detail. 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?
Given zero parameters and no output schema, description should clarify the tool's scope and behavior. It does not, leaving significant ambiguity.
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), so description doesn't need to explain params. However, the bare description adds no semantic value beyond the name.
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?
Description 'List all messages' does not specify which messages (conversation-wide or account-wide). The name 'list_all_conversation_messages' suggests per-conversation, but no parameters confirm. Sibling tools like 'list_all_messages' and 'get_conversation_messages' add confusion.
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 siblings (e.g., 'list_all_messages', 'get_conversation_messages'). No context about filters or preconditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 'Update' implying mutation, but no details on authorization, side effects, or what happens to existing data. Fails to compensate for missing 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?
Extremely short but lacks necessary detail; it is under-specified rather than concise. Every sentence should earn its place, and this single sentence 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?
For an update operation with no output schema, the description should indicate which fields can be updated and how the contact is identified (e.g., by ID). It provides none of this, making it completely 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?
Input schema has zero parameters, so schema coverage is 100%. Description adds no value beyond the schema, but baseline is 3 as no parameter information is needed.
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?
Description 'Update a contact' is a tautology of the tool name, providing no additional specificity. Does not differentiate from sister tool 'contact_update' which likely performs the same 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 versus alternatives like 'contact_update' or other contact operations. Lacks 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, and the description provides no behavioral details (e.g., destructive effects, authentication needs, side effects). The agent has no insight into what updating an integration hook does.
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 (4 words) but merely restates the tool name, adding no value. Every word should earn its place; here it's tautological.
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 schema content, no output schema, and no annotations, the description should provide substantial context. It fails to explain what an integration hook is, what update operation does, or when to use it. Completely inadequate.
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 defined; schema coverage is trivially 100%. With zero params, the baseline of 4 is appropriate. Description adds no extra meaning but is not required to.
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 'Update an Integration Hook', which is clear in verb and resource, but does not differentiate from sibling tools like 'create_an_integration_hook' or 'delete_an_integration_hook'. No additional specificity about what updating entails.
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 (e.g., create/delete hooks). 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.
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 whether the update is partial or full, required permissions, side effects, or idempotency. The agent has no insight 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely brief (one phrase), which is under-sized for a mutation tool with a complex parameter. While front-loaded, it sacrifices necessary information for brevity.
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 (mutation, one complex param, no output schema, no annotations), the description is grossly incomplete. It fails to explain what the update entails, what the response looks like, or any operational 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 single parameter 'sla_policy' is a complex object reference with 0% schema description coverage. The description does not clarify which fields can be updated or any constraints, leaving the agent to guess the expected 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?
The description 'Sửa chính sách SLA' (Edit SLA policy) clearly states the verb (edit) and resource (SLA policy), distinguishing it from sibling tools like create, get, delete, and list. However, it is in Vietnamese, which may reduce clarity for non-Vietnamese agents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps 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_sla_policy, get_sla_policy). There is no mention of 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 a creation action. No information is given about required permissions, side effects, idempotency, or what occurs if the agent 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (4 words), but it omits critical information. Conciseness is achieved at the cost of clarity, making it less useful.
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 sibling tools and the lack of annotations and output schema, the description is severely incomplete. It does not explain the tool's role, input expectations, or output, leaving the 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?
There are no parameters, so the schema coverage is 100%. The description adds no meaning beyond the schema, but the absence of parameters is unusual for an 'add' tool; the description does not clarify why no input is needed.
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 'Add a New Agent' is a tautology that merely restates the tool name without specifying context (e.g., account, inbox, team). It lacks distinction from sibling tools like 'add_new_agent_to_inbox' or 'add_new_agent_to_team'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 when this tool is appropriate or what prerequisites 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. The description does not disclose behavioral traits such as whether the agent already exists, permission requirements, or side effects of adding to a team.
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 (4 words) but lacks critical context. It is not appropriately sized; 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?
Given no annotations and no output schema, the description should provide more. It fails to explain what 'New Agent' means or that it refers to adding a user to a team. Incomplete for the tool's 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?
Schema coverage is 100% with a clear description for user_ids. The description adds no additional meaning beyond the schema, meeting baseline expectations.
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?
Description is 'Add a New Agent', which is vague. The tool name includes 'to_team' but the description omits this, failing to specify that the agent is being added to a team. This could be confused with adding an agent to an account or inbox.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 'add_new_agent_to_account' or 'add_new_agent_to_inbox'. No exclusions 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 must convey behavioral traits. It only implies a write operation ('add') but does not disclose prerequisites, side effects, 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise but at the expense of necessary detail. A single vague sentence does not earn its place; it lacks structure and front-loading of critical 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 no parameters, no output schema, and no annotations, the description should at least clarify what an 'article' refers to in this context. It does not, leaving the tool indistinguishable from similar 'add_new' 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 has zero parameters, so schema coverage is trivially 100%. The description adds no additional meaning beyond what the schema states. With no 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.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description merely restates the name 'Add a new article' without specifying the type of article or context. Among many sibling 'add_new_*' tools, it does not differentiate what makes this unique (e.g., knowledge base article vs. something else).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 numerous 'add_new' tools for different entities, but the description offers no selection criteria.
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 cover behavioral traits. It only says 'Add Labels' with no info on whether it adds to existing labels or replaces, permissions needed, side effects, or error conditions. This is a severe 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (2 words), but it under-specifies rather than being efficiently concise. It lacks structure and fails to convey essential information, so it does not earn 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 lack of output schema and annotations, the description should provide context about the tool's purpose, input constraints, and outcome. It only states 'Add Labels', which is incomplete for an agent to use it correctly without prior 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?
With 100% schema coverage, the schema already describes the 'labels' parameter as an array of comma-separated strings. The description adds no further meaning beyond what's in the schema, so a baseline of 3 is appropriate.
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 'Add Labels' is minimal but states a verb and resource. However, it lacks specificity about the target (contact) and could apply to other entities, though the tool name clarifies it's for contacts. It's barely above a tautology.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents 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 or alternatives are provided. There are sibling tools like 'list_all_labels_of_a_contact' and 'conversation_add_labels' that could be confused, but the description offers no help in differentiating when 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, but it only states the verb 'Create'. It does not disclose any side effects, required prior actions, or what happens when a conversation is created without input parameters.
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 but tautological, wasting the opportunity to provide value. It is not structured to highlight 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?
Given the complexity of conversation creation and many sibling tools, the description is incomplete. It does not explain what kind of conversation is created, how it differs from other creation tools, 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.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (no parameters), so the baseline is 3. However, the description adds no meaning beyond the schema, leaving ambiguity about how a conversation is created without inputs.
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 'Create a conversation' is a tautology that restates the tool name 'create_a_conversation'. It does not distinguish from the sibling tool 'new_conversation', which likely serves 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 'new_conversation'. There is no context about 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 should disclose behavior (e.g., read-only operation, authentication needs, return structure). It provides none of that, offering only a vague 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 short sentence with no extraneous words. However, it sacrifices information 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 absence of annotations and output schema, the description should provide enough context for correct tool use. It omits crucial details like how to specify the team and what the output contains, making it 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?
Although there are zero parameters (schema coverage 100%), the description fails to explain how the tool identifies the target team (e.g., via path parameter). The baseline of 4 is not justified because the description adds no clarifying context beyond the schema.
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 'Get a team details' essentially rephrases the tool name without adding specificity. It does not distinguish this tool from sibling tools like list_all_teams or clarify what 'details' include.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 that it fetches a single team (contrast with list_all_teams) or how to specify which team.
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 bears full responsibility for disclosing behavioral traits. It fails to mention whether the tool is read-only, what output to expect, or any side effects. This is a critical 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 very short (four words) and lacks a complete sentence. While concise, it sacrifices clarity and structure. It is not verbose, but it is underspecified.
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 zero parameters, no output schema, and no annotations, the description should provide sufficient context about what the tool does, what data it returns, and how it differs from similar tools. It fails to do so, leaving the agent with minimal guidance.
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 schema coverage is 100%. The description does not need to explain parameters, but it also does not add any additional context about the tool's function beyond the name.
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 'Get Account reports summary' conveys a verb and resource, but it is vague and does not distinguish itself from sibling tools like list_all_conversation_statistics or get_account_conversation_metrics. The meaning of 'reports summary' is unclear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents 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 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?
With no annotations, the description must disclose behavioral traits, but it does not. It fails to mention that the tool sets a specific status (not toggles), or any side effects, permissions, or response behavior.
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 minimal (two words), sacrificing informativeness for brevity. It does not effectively balance conciseness with 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?
Despite only two parameters and full schema coverage, the description is incomplete. It does not explain the overall effect (setting conversation status), return values, or how it differs from similar 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?
Since schema description coverage is 100%, the baseline is 3. The description adds no additional meaning beyond the schema, which already documents the parameters and enums.
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 'Toggle Status' is a tautology, essentially restating the tool name without specifying the resource (conversation) or the available statuses. It does not clarify that the tool sets a conversation status rather than toggling between two states.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 sibling tools like 'resolve_conversation' (which sets status to resolved) or other status-related tools. 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?
The description only states the action 'Delete', implying a destructive operation, but no annotations are provided. It does not disclose side effects, required permissions, or any 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one sentence), but it adds no value beyond the tool name. It is not verbose, but it also does not earn its place by providing additional clarity or guidance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 parameters, no output schema, and no annotations, the description is insufficient. It does not explain how the label is identified (e.g., via context or a previous step), what happens upon deletion, or any dependencies.
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 (100% coverage), so the schema itself documents everything. The description adds no parameter information, but the baseline score of 3 is appropriate since no additional semantic context is needed.
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 'Delete a label' is a tautology of the tool name and adds no new information. It clearly indicates the action and resource, but fails to distinguish from other label operations beyond the verb, and does not add 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. The description does not mention prerequisites, post-conditions, or situations where another tool (e.g., update_a_label, list_all_labels) 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, and the description does not disclose behavioral traits such as idempotency, error responses (e.g., what if namespace doesn't exist), or permission requirements. The description carries the full burden but offers 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (5 words), which is concise but at the cost of essential information. It does not fully earn its place; a few more words could dramatically improve utility. It is under-specified rather than efficiently complete.
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 (single param, no output schema) and the presence of closely related siblings (list, put, claim, delete), the description is far from complete. It omits return value, behavior, parameter details, and usage context. The agent cannot effectively select or invoke this tool based solely on the description.
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 'namespace' (type string) with no description, and the schema description coverage is 0%. The description does not explain what 'namespace' represents or any constraints (e.g., format, required). There is no added semantic 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 'Get one automation state entry' clearly states the verb (Get) and resource (automation state entry), and the singular 'one' implies it retrieves a single entry, distinguishing it from sibling 'list_automation_states' which retrieves multiple. Slightly more specificity could be achieved by noting it's by namespace.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 'list_automation_states' (for listing all) or 'put_automation_state' (for creating/updating). The description lacks explicit 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 exist, and the description discloses no behavioral traits. It fails to indicate whether the operation is read-only, has side effects, requires authentication, or any other relevant behavior. The description provides no transparency beyond the bare 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 short (3 words) but at the expense of necessary detail. It is under-specified, not concise. A single sentence that adds no differentiating or clarifying information 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 no parameters, no output schema, and no annotations, the description should fully explain the tool's behavior. It does not specify what conversation is retrieved, how it is fetched, or what data is returned, leaving significant gaps for an agent to correctly invoke 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 no parameters, so schema coverage is 100%. With zero parameters, the description does not need to add parameter-specific meaning. Baseline is 4, and no additional clarification is required from the description for parameters.
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 'Get a single conversation' indicates the action and resource, but is vague. It does not specify which conversation is retrieved or how it is identified, especially since the input schema has no parameters. This lack of clarity is compounded by similar sibling tools like 'get_details_of_a_conversation', creating 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?
No guidance is provided on when to use this tool versus alternatives. The description does not mention any prerequisites, context, or distinguish it from related conversation tools such as 'get_details_of_a_conversation' or 'list_all_contact_conversations'.
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 idempotency, authentication requirements, error handling, or side effects. It fails to add any value 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one phrase), but it sacrifices clarity and structure. It is front-loaded but lacks detail. Adequate for a simple tool, 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 the minimal schema (only an ID parameter) and no output schema, the description is too sparse to fully guide an agent. It does not explain the expected request body, behavior on success/failure, or how the update is performed.
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 'id', so the description adds no additional semantic meaning. Per guidelines, baseline 3 is appropriate.
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 'Update automation rule in Account' clearly states the action and resource, but it is essentially a rephrasing of the tool name. It does not elaborate on what aspects of the rule can be updated or how it differs from sibling tools like add_new_automation_rule_to_account.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_new_automation_rule_to_account or delete_automation_rule_from_account. There is no context about 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, description must disclose behavior. Merely stating 'Update' without details on side effects, idempotency, or what fields change leaves significant gaps. The tool name implies a connection to an account, but this is not explained.
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 phrase lacks substantive content required for a useful tool description. Conciseness is achieved at the expense of completeness and 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 no output schema and no annotations, the description should provide richer context (e.g., what attributes are updatable, return format, etc.). Currently it is too minimal 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.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so baseline 4 applies. The description could clarify that no parameters are needed (or why), but the absence is acceptable. The empty schema fully covers the parameter space.
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?
Description 'Update a portal' is a tautology that restates the tool name without clarifying what 'portal' refers to or how it relates to 'account'. It fails to distinguish from sibling tools like 'add_new_portal_to_account' or 'get_portal'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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, required state (e.g., portal must exist), or when to prefer creation vs update.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 convey behavioral traits. It only mentions fetching counts, leaving unclear aspects like read-only nature, side effects, authentication needs, or rate limits. The minimal text fails to disclose these key behaviors.
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 (4 words) but omits critical details, making it under-specified rather than efficiently concise. It sacrifices completeness for brevity, scoring average on this dimension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 optional parameters and no output schema, the description should explain the return format (e.g., separate counts per status) and how parameters affect results. It fails to provide this context, leaving the agent uninformed about what 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 information about the parameters beyond what the schema provides. With schema description coverage at 40% (only 'q' and 'status' have descriptions), the description should clarify ambiguous parameters like 'labels', 'team_id', and 'inbox_id', 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 Conversation Counts' clearly states the tool's function as retrieving counts of conversations, distinguishing it from sibling tools like 'conversation_list' that list conversation details. However, it does not specify whether counts are aggregated or per status, slightly reducing 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?
No guidance is provided on when to use this tool versus alternatives such as 'conversation_list' or 'conversation_filter'. The tool's purpose of getting counts is distinct, but the description lacks explicit usage context, such as 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. The description implies mutation ('Create') but discloses no behavioral traits such as authentication requirements, side effects, 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 concise (one sentence) but lacks structure. It is insufficiently informative for a tool that likely requires input data.
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 parameters, no output schema, and no annotations, the description is severely incomplete. It fails to clarify how to create a contact or what response to expect.
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 properties, so schema description coverage is 100%. However, the description adds no meaning beyond the schema; it does not explain why the tool has no parameters or what defaults apply.
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 and resource ('Create a contact') but is overly vague. It does not specify what creating a contact entails or distinguish itself from sibling tools like contact_create.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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., contact_create, update_a_contact). The description provides no 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations and only a generic description, the behavioral traits are absent. The agent cannot infer side effects, required permissions, or whether this is a mutation—essential 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but under-informative. It lacks the detail that would make it genuinely helpful, striking a balance between brevity 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?
Despite the tool being simple (0 params, no output schema), the description fails to provide context about what a data source is or how it integrates with other tools. Given the 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.
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%. There is nothing to explain beyond what the schema provides, so the description is adequate.
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 'Create a data source' states the action and resource, distinguishing it from sibling tools like list_data_sources, get_data_source, etc. However, it lacks specificity about what a 'data source' is or what the creation entails, making it only minimally 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?
No guidance is provided on when to use this tool versus alternatives such as test_data_source or update_data_source. The description offers no context about prerequisites or scenarios, so agents lack 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 carries full burden. It only states 'Get' but does not confirm read-only nature, auth requirements, or any side effects. The schema description incorrectly says 'to be updated', contradicting the tool's name, but the tool description itself 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one sentence), but it is front-loaded with the purpose. However, it lacks substance; it does not add value beyond the tool name. Conciseness is acceptable but not optimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 schema, the description still fails to explain what 'details' are returned or any special behavior. No output schema, so description should clarify but does not. The tool is incomplete 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 coverage is 100% (1 parameter, id, with description). The tool description adds no additional meaning beyond the schema. The schema description includes a misleading 'to be updated' phrase, but the tool description does not correct or enhance it.
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 a custom attribute details', which is a clear verb+resource pair. However, it does not differentiate from sibling tools like 'get_account_custom_attribute' (also in the list), leading to potential confusion. The purpose is understood but not uniquely 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 guidance is provided on when to use this tool versus alternatives (e.g., get_account_custom_attribute, list_all_custom_attributes). No context, prerequisites, 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.
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 whether it returns a full list, supports pagination, or requires permissions. It adds no value 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (4 words), but it omits essential context. It is not efficient because it fails to provide useful information 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?
With no parameters and no output schema, the description should clarify what is listed (e.g., flow IDs, names) or any default scope. It does not, leaving the agent uncertain about the tool's output.
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 description does not need to add parameter information. Baseline score of 4 is appropriate.
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 'List scheduled flows' is a clear verb+resource pair, but it does not distinguish this tool from sibling list tools like list_all_contact_conversations or list_all_conversation_messages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 any prerequisites 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 are present, and the description does not disclose behavioral traits such as whether the action is idempotent, what side effects occur, or how it interacts with other conversation properties. The inconsistency between 'toggle' and the enum parameter is not clarified.
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 too brief (two words) to be informative. It lacks context and structure, making it under-specified rather than concisely 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?
For a tool with a single parameter and no output schema, the description should at least clarify the action semantics (set vs toggle) and provide minimal usage context, especially given the many sibling conversation tools. It fails to do so.
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% and the parameter description already explains it as 'the priority of the conversation'. The tool 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.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Toggle Priority' indicates the tool changes the priority of a conversation, but 'toggle' implies switching between two states while the schema allows setting one of five priority levels, making the purpose slightly imprecise. It does not explicitly state the target resource (conversation) beyond the 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 like 'update_conversation' or 'toggle_status_of_a_conversation'. There is no mention of prerequisites or context for its 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 carry the full burden. It only states the action without disclosing side effects, permissions, or whether it is a write operation.
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 necessary context. It is under-specified, failing to earn its place by providing minimal helpful 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?
Despite low complexity, the description omits critical context such as the scope of the typing status. It is incomplete for effective tool 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?
Schema description coverage is 100%, as the single parameter 'typing_status' has a description. The tool description adds no additional meaning beyond the schema, meeting the baseline for high coverage.
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 'toggle' and resource 'typing status', but it lacks specificity regarding what typing status is being toggled (user's own vs. conversation level). This creates ambiguity given the sibling tool 'toggle_typing_status_of_a_conversation'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 'toggle_typing_status_of_a_conversation'. The description does not indicate 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, so the description carries the full burden. It only says 'Update user profile' without disclosing behavioral traits such as side effects, required permissions, or whether password updates need current_password.
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 cost of informativeness. It could be expanded to include key details 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 the complex nested parameter, zero schema descriptions, no output schema, and no annotations, the description is critically incomplete. It fails to convey required fields, validation rules, or expected outcomes.
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 in the schema properties). The description adds no meaning to the 'profile' parameter, which is a complex nested object with multiple fields. It does not explain any field semantics 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 'Update user profile', which clearly indicates the verb (update) and resource (user profile). It is distinct from siblings like fetch_profile (read) and update_account (account-level), but lacks differentiation from similar update 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 update_account or fetch_profile. The description implies usage for updating profile fields, but does not specify 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, so the description bears full responsibility for disclosing behavioral traits. It fails to mention any side effects, permissions required, or what happens if the flow doesn't exist. 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (one sentence) but lacks substance. It is under-specified rather than concise, as it fails to provide useful information beyond the tool 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 has no parameters, no output schema, and no annotations, the description should explain how to specify which flow to update and what 'update' entails. It fails to do so, making it inadequate for an agent to invoke 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 has zero parameters, so schema_description_coverage is trivially 100%. The description adds no additional meaning beyond the schema. 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 'Update' and the resource 'a scheduled flow', distinguishing it from sibling tools like delete, create, get, run, and list. However, it is essentially a restatement of the tool name, adding minimal new 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, no prerequisites, and no context about typical usage scenarios. It simply states what the tool does.
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 such as side effects, required permissions, or post-creation behavior. The agent is left completely in the dark about what happens when the tool is invoked.
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, but it does not earn its place because it adds no value beyond the tool name. It lacks necessary context and behavioral 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 no output schema or annotations, the description should provide sufficient context. It fails to explain what a scheduled flow is, what inputs are required (if any), or what the outcome looks like. The description is severely incomplete.
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 schema coverage is 100%. With zero parameters, the baseline is 4. The description does not need to add parameter details since none exist.
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 scheduled flow' clearly states the action and resource. It is specific, but does not differentiate from other create tools among siblings. However, within the scheduled flow context, it is the only create tool, so distinction is implicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_scheduled_flow or run_scheduled_flow. 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 carries the full burden of behavioral disclosure. It does not state that this is a read operation, whether it requires authentication, what it returns, or any side effects. The description is too minimal to inform an AI agent 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 a single sentence and is concise in terms of word count, but it is under-specified. Conciseness should be balanced with informativeness; here, the brevity sacrifices clarity and completeness, making it less useful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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, so the description should explain what the tool returns. It does not describe the return value, format, or any contextual behavior. Given the tool's simplicity (no parameters) and the presence of a sibling, the description is insufficient for an agent to understand its purpose and 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 has zero parameters with 100% coverage, so the schema already describes all parameters. The baseline is 4, but the description adds no extra semantics about the tool's operation or expected input. It is a bare statement that does not enhance understanding 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 'Get CSAT survey page' with a clear verb and resource, but 'page' is ambiguous—it could refer to a single survey page or a page of results. It does not distinguish from the sibling tool 'list_csat_survey_responses', which likely lists responses, whereas this tool might fetch a single page object. The purpose is vague and lacks 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?
No guidance is provided on when to use this tool versus alternatives. The sibling 'list_csat_survey_responses' is closely related, but the description does not clarify the difference or suggest use cases. There is no context about 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?
No annotations exist, and the description does not disclose read-only nature, pagination, or output format. The limit parameter suggests pagination but is not 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 concise at one sentence, but it under-specifies essential information. It sacrifices clarity for brevity.
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 many sibling state tools, the description is completely inadequate. It fails to explain what automation states are, the response format, or how namespace filters 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 adds no meaning to parameters. Schema coverage is partially descriptive, but the critical 'namespace' parameter lacks description. The tool description does not clarify parameter roles.
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 'automation state entries', distinguishing from singular 'get_automation_state'. However, it lacks details on scope and what the entries represent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 'get_automation_state'. No context on required namespace 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?
The description 'Update' implies mutation, but no behavioral details are disclosed, and no annotations are present to fill in gaps. Side effects, permissions, and scope are unspecified.
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 is overly minimal and 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?
With no parameters, no output schema, and no annotations, the description provides almost no actionable information for an AI agent. It lacks identification of the webhook, update fields, and prerequisites.
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 description does not need to add schema details. However, it fails to explain how the target webhook is identified, which is a critical omission.
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 'Update a webhook object' which is a clear verb+resource, but it is vague on how the specific webhook is identified. With no parameters, the mechanism is unclear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 other webhook tools like create, list, or delete. No context for when to apply.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 an update occurs, with no details on permissions, side effects, idempotency, or limitations. For a mutation tool, more behavioral context 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence), but it is underspecified. It is concise in terms of word count but lacks structure and detail, resulting in minimal information density.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 a single parameter, the description is incomplete. It does not explain what fields are updated (the schema only has id, implying possible optional fields), nor does it describe the response 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 input schema has 100% coverage for the single required parameter 'id', which is described adequately. The 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.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description restates the tool name almost verbatim, which is borderline tautology. It does convey the verb and resource ('Update Canned Response in Account'), but adds no further context to distinguish it from sibling tools with 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 is provided on when to use this tool versus alternatives like get_account_canned_response, add_new_canned_response_to_account, or delete_canned_response_from_account. 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It fails to mention any side effects, required permissions, rate limits, or what the webhook creation entails. The description adds no value beyond the generic 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 extremely concise with a single phrase. While it is well-structured and front-loaded, it sacrifices completeness for brevity.
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 very incomplete given no output schema and no annotations. It does not explain what a webhook is, what the response will be, or any side effects. For a create operation, this is insufficient.
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 baseline is 4. However, the description does not add any additional meaning or context about the operation, so it does not improve understanding 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 'Add' and resource 'webhook', making the primary action obvious. However, it does not differentiate from sibling tools like update_a_webhook, but the name itself implies 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 on when to use this tool versus alternatives such as update_a_webhook or delete_a_webhook. 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 carry full burden. It indicates a destructive action but lacks specifics on irreversibility, dependencies, or side effects. 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single concise sentence that conveys the core purpose. No wasted words, though it could benefit from 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?
For a deletion tool with no output schema and an opaque parameter, the description is insufficient. It does not explain the concept of automation state or the namespace, making it hard 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.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage; the description adds no meaning to the 'namespace' parameter. The agent is left without understanding what value to provide.
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 (automation state entry), making the tool's purpose immediately understandable. However, it does not explicitly differentiate from sibling tools like put_automation_state or get_automation_state, though the action is distinct.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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., delete_automation_rule_from_account, put_automation_state). No context about 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 are provided, and the description does not disclose any behavioral traits such as authentication requirements, side effects, or scope. It fails to add value beyond a basic 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with a single sentence. It is front-loaded and efficient, but it may be too terse, lacking necessary details for 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 no parameters and no output schema, the description should explain how to specify the conversation or what the response format is. It does not provide this context, leaving the tool's usage underdefined.
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 (100% schema coverage), so the description cannot add parameter-level semantics. However, the description does not explain how the conversation is identified or what messages are returned, missing an opportunity to compensate for the lack of parameters.
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 'Get messages from a conversation' uses a verb+resource structure, but it does not differentiate from the sibling tool 'list_all_conversation_messages', which likely performs the same action. The purpose is generic and lacks 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?
There is no guidance on when to use this tool versus alternatives, especially the very similar 'list_all_conversation_messages'. No context for when it should or should not be used 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 are provided, but the description only says 'Get details' without explaining what details are returned, authentication needs, or rate limits. 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded, but it lacks essential information. It is concise but not sufficiently 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 no output schema, the description should hint at the return value (e.g., full automation rule object). It does not, and the parameter description contains a misleading note.
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 says 'to be updated' which conflicts with a GET operation. The description adds no further 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 it retrieves automation rule details with the verb 'Get'. However, it does not differentiate from the sibling tool 'get_account_automation_rule', which could have 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 on when to use this tool vs. alternatives like 'get_account_automation_rule' or prerequisites for using the 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 solely bears the burden of behavioral disclosure. It only states a read-like operation but does not reveal permissions, pagination, or any constraints, leaving significant gaps.
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 of 4 words, efficiently stating the purpose. It 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.
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 explain what response to expect, but it does not. Additionally, the tool's context (e.g., which inbox) is missing, 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 has 0 parameters and 100% schema description coverage, so the baseline is 3. The description adds no parameter information, but none is needed. It is adequate for this parameterless tool.
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 'List Agents in Inbox' states a specific verb ('List') and resource ('Agents in Inbox'), but without specifying which inbox, it is vague. The name suggests getting members of a particular inbox, but no inbox identifier is mentioned, 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 provided on when to use this tool versus alternatives like get_team_members or add_new_agent_to_inbox. There is no context for when 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, and the description does not disclose behavioral traits (e.g., pagination, ordering, data retention). It simply states the action 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.
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 completeness, leaving out necessary parameter and behavioral 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?
For a tool with one parameter and no output schema, the description lacks essential context like the meaning of 'limit' and whether results are paginated. It is insufficient for an agent to reliably 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?
The only parameter 'limit' is left unexplained; the description adds no meaning beyond the schema's default and maximum values. With 0% schema description coverage, the tool relies entirely on the description to clarify parameter intent, 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 verb 'list' and resource 'past runs of a flow', distinguishing it from sibling tools like 'list_scheduled_flows' which list flows themselves. However, it lacks scope details like 'all' or 'recent'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_scheduled_flow' or 'run_scheduled_flow'. 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?
The description indicates mutation ('update') but does not disclose side effects, required permissions, or return value. 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise but under-specified. It lacks any structure or additional information to aid the agent.
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 zero parameters, no output schema, and no annotations, the description fails to explain how to identify which filter to update or any other crucial details. 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?
There are no parameters in the schema, so schema coverage is 100% by default. The description adds no meaning beyond the schema, which is adequate for zero parameters but does not compensate for missing 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 'Update a custom filter' clearly states the verb 'update' and the resource 'custom filter', distinguishing it from sibling tools like create, get, and delete. However, it does not specify what attributes 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 such as create or delete. 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 for behavioral disclosure. It only states the action without revealing side effects (e.g., whether it creates a new record or updates an existing one), required permissions, 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At two words, the description is extremely concise but lacks structure. It is not a complete sentence and fails to earn its place by providing additional context 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 three parameters and no output schema, the description is incomplete. It does not explain the tool's role in the contact-inbox relationship or its usage within the broader system, leaving the agent without sufficient 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 100%, so the baseline is 3. The description adds no extra meaning beyond the schema's parameter descriptions. It does not explain the purpose of source_id or how parameters relate.
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 contact inbox' is a clear verb+resource pair indicating the tool creates an association between a contact and an inbox. It is distinct from sibling tools like 'create_a_contact' or 'create_a_conversation', though it does not explicitly differentiate 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 Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. There is no indication of prerequisites (e.g., contact and inbox must already exist), when to use this vs. alternatives, or potential constraints like duplicate checking.
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 fully disclose behavior, but it only states 'Delete', missing details like destructiveness, irreversibility, permission requirements, or effect on associated data. This is a critical omission.
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 brief (3 words) but lacks substance. While concise, it does not earn its place as it merely repeats the tool name without adding useful 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 simplicity of a delete operation with no parameters or output schema, the description should at least note that the action is permanent or requires an identifier. It fails to provide enough context for safe invocation.
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 schema description coverage is 100% (trivially). The description cannot add param info, so a baseline of 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 'Delete an AgentBot' clearly states the verb and resource, and distinguishes from siblings like create, get, update, and list agent bot tools. However, it is essentially a restatement of the tool name without added 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?
No guidance is provided on when to use this tool or what prerequisites exist. There is no mention of alternatives or when not to use it, 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.
Behavior1/5
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 simply states 'Delete a team' without mentioning side effects (e.g., cascade deletion of members), authentication requirements, or rate limits. The agent is left guessing the 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?
The description is extremely short (3 words) and front-loaded, but it is too terse for a delete operation that may have significant impact. It earns no extra sentences, but the lack of detail makes it feel 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?
Given the absence of an output schema and annotations, the description should provide more completeness. For a delete tool, important context like irreversibility, dependencies (e.g., team must exist), or confirmation steps is missing. The description is insufficient for safe usage.
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 schema description coverage is 100%. Per the guidelines, 0 parameters yields a baseline of 4. The description adds no parameter details, but none are needed; the tool's action is self-contained.
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 'Delete a team' clearly states the verb (delete) and resource (team), making the tool's purpose obvious. However, it does not differentiate from sibling tools like delete_agent_in_team, which deletes a team member, not the team 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 is provided on when to use this tool versus alternatives (e.g., delete_agent_in_team). There is no mention of prerequisites, such as the team needing to exist or be empty before deletion. The description lacks any 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?
With no annotations provided, the description carries full burden for behavioral disclosure. It only says 'Xoá' (delete), implying a destructive action, but provides no details on side effects, irreversibility, confirmation steps, or error states.
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 (4 words) but omission of critical details (like what policy is deleted, consequences) makes it underspecified rather than concise. Every word is not 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?
Given no parameters, no annotations, and no output schema, the description should provide more completeness. It fails to explain the scope of the deletion, prerequisites, effects, or confirmation. It is inadequate for a potentially 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?
Zero parameters, so baseline is 4 per rules. However, the description does not clarify how the tool identifies which SLA policy to delete (e.g., implicitly based on context or an identifier elsewhere). This missing nuance reduces the score.
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 'Xoá chính sách SLA' (Vietnamese for 'Delete SLA policy'), which clearly identifies the verb (delete) and resource (SLA policy). It distinguishes from sibling tools like create, get, update, list. However, using Vietnamese while other tool names and schemas are in English may cause confusion for an English-oriented 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?
No guidance on when to use this tool or when not to. It does not mention prerequisites, such as ensuring the policy is not in use or that the user has appropriate permissions. No alternatives are suggested.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 bears full responsibility for behavioral disclosure. It only states the action without revealing side effects, required permissions, rate limits, or whether the data is cached or real-time. The agent has no behavioral insight beyond the obvious 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one short phrase), which is efficient, but it sacrifices completeness. For a tool with zero parameters and no output schema, more context could have been added without sacrificing brevity. It is not optimally 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 should provide more contextual information such as what 'account details' includes (e.g., name, email, settings) or whether it returns a full object. The single phrase is insufficient for an AI agent to fully understand the tool's capabilities.
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 is empty (0 parameters), so the description does not need to explain parameters. Schema description coverage is 100% (vacuously), so the baseline of 4 applies. No additional parameter information is necessary.
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 'Get account details' clearly identifies the action (get) and resource (account details), but it is vague and does not specify what kind of details (e.g., basic info, settings, or audit logs) or differentiate from sibling tools like get_account_audit_logs or update_account. It lacks specificity to fully guide an AI 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?
No usage guidance is provided. The description does not indicate when to use this tool versus alternatives such as get_account_audit_logs or update_account, nor does it mention any 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?
No annotations are provided, and the description does not disclose any behavioral traits such as side effects, permissions required, or whether the tool is read-only. The minimal description fails to inform the agent 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 extremely concise at two words, but it lacks structure and detail. It could benefit from additional context without being 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?
Despite having no parameters, the tool likely returns data, but the description does not specify what details are included. There is no output schema, so the description should compensate. The current description is incomplete for an agent to understand the tool's output.
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, and the description does not add any parameter semantics. However, since there are zero parameters, the baseline is 4. The description could be improved by confirming the tool takes no parameters.
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 'Inbox details' indicates the tool retrieves details about an inbox. However, it is vague and does not distinguish from sibling tools like 'get_inbox' or 'list_all_inboxes'. The name suggests a specific inbox, but the description lacks clarity on what exactly 'details' 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?
No guidance is provided on when to use this tool versus alternatives. Given sibling tools like 'get_inbox' and 'list_all_inboxes', the description should clarify the difference but does not.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 gives no behavioral details beyond 'Get'. It does not disclose side effects, auth requirements, or expected scope.
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 with no extraneous words, making it maximally 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?
The description lacks essential context: what a scheduled flow is, how to identify it, and what the output contains. This is incomplete for a tool with no output schema or 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?
There are no parameters, and schema coverage is 100%. The description adds no parameter information, which is acceptable given the baseline for high coverage.
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 'Get a scheduled flow' states the verb and resource clearly but does not differentiate from sibling tools like list_scheduled_flows, making it only minimally 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?
No guidance is provided on when to use this tool versus alternatives such as list_scheduled_flows or other retrieval 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. The description only states 'List SLA policies' with no details on return format, pagination, authentication requirements, or side effects. Fails to disclose essential 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?
Single sentence is concise but lacks structure. Could front-load key behavioral details. No wasted words, but also no substantial content 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?
For a simple list tool with no parameters and no output schema, the description is incomplete. Does not mention what is returned (e.g., list of SLA policy objects), pagination, or filtering capabilities.
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?
Input schema has 0 parameters, so schema description coverage is trivially 100%. Description does not need to add parameter details. Baseline 4 for zero-parameter 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 tool name 'list_sla_policies' clearly indicates a list operation on SLA policies. The description in Vietnamese confirms this, though language mismatch may slightly hinder clarity for English-centric agents. Distinguishes from sibling create/get/update/delete 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 get_sla_policy. No context on typical use cases, 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 carries full burden for behavioral disclosure. It only says 'Read', implying a non-destructive operation, but fails to mention authentication, rate limits, result format, or other important 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 extremely concise at 4 words, but this conciseness sacrifices clarity. It is not verbose but lacks essential detail, 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 no parameters, no output schema, and no annotations, the description is insufficient. The tool likely requires implicit context (e.g., which data source to query), but the description provides none, leaving the agent uninformed.
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 in the input schema (100% coverage), so the description does not need to explain parameters. Baseline 4 is appropriate, though the description adds no further 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?
Description states 'Read from the data source', which is a specific verb+resource but remains vague. It does not distinguish from sibling 'get_data_source' which likely retrieves metadata, whereas 'query_data_source' probably executes a query. The purpose is unclear without additional 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 on when to use this tool versus alternatives like 'get_data_source' or 'test_data_source'. The description lacks context for appropriate 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 are provided, and the description fails to disclose any behavioral traits. The agent cannot infer whether this tool makes network calls, modifies state, or requires authentication. The description carries the full burden but 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 extremely concise (three words). While appropriate for a trivial action, it lacks any structural elements like front-loading key info. It is not verbose but could be slightly more descriptive without adding unnecessary 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 tool's simplicity (0 params, no output schema), the description is minimally complete. However, it fails to provide context about what 'testing' involves or its relationship to sibling tools. A more complete description would mention the expected result or side effects.
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 with 100% schema coverage, so the description needs no additional parameter information. The baseline for no parameters is 4, and the description adequately conveys that no inputs are 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 'Test the connection' combined with the tool name 'test_data_source' clearly indicates the tool's purpose: to test a data source connection. It is specific enough to distinguish from other operations like creating or listing data sources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps 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. Among siblings like 'list_data_sources' or 'get_data_source', there is no mention of prerequisites, typical scenarios, or situations where testing 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?
The description only states 'Toggle Typing Status' without disclosing behavioral traits such as side effects (e.g., whether it sends a typing indicator, updates conversation state, or is reversible). With no annotations, the description carries the full burden and fails to inform the agent of what happens when invoked.
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?
At two words, the description is excessively terse and under-specified. While it is front-loaded, it sacrifices clarity and fails to convey necessary context, making it more of a placeholder than a concise description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 (2 params, no output schema, no annotations), the description is incomplete. It does not explain what 'typing status' means, the effect of toggling, or any context like participation requirements. Sibling tools offer no differentiation cues.
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%, so the baseline is 3. The description adds no information about the parameters ('is_private' and 'typing_status') beyond what the schema already provides, so it does not improve 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 'Toggle Typing Status' clearly indicates a verb ('Toggle') and a resource ('Typing Status'), providing a basic understanding of the tool's action. However, it lacks specificity about the context (e.g., for a conversation) and could be confused with sibling 'toggle_typing_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 is provided on when to use this tool versus alternatives like 'toggle_typing_status' or other conversation-related tools. There is no mention of prerequisites, exclusions, 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 simply states 'Update' without disclosing whether the operation is destructive, reversible, requires authentication, or has side effects. The behavioral impact is entirely opaque.
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 structure and fails to front-load critical information. It is minimally acceptable but could be expanded for 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 no output schema, no annotations, and no parameters, the description should provide substantial context about the tool's operation. It does not explain what the layout is, what fields are updated, or any constraints, 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.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so baseline is 4. The description does not add any parameter-specific information, but since no parameters exist, the baseline applies. However, the description could explain the nature of the update (e.g., what fields are affected).
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 'Update account branded email layout' restates the tool name, providing a clear verb and resource but without any differentiation from sibling tools. It is not a tautology since it adds the word 'Update', but it lacks specificity about scope or 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 like 'get_account_branded_email_layout' or other update tools. There are no conditions, 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, and the description does not disclose behavioral traits such as required permissions, side effects, or input constraints. The agent is left uninformed about the tool's 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?
A single sentence is highly concise, but it sacrifices informativeness. It is front-loaded but lacks substance 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?
For a creation tool, the description is incomplete. It does not specify what fields or configuration the automation rule requires, nor what the response contains. The empty input schema suggests missing documentation or a questionable design.
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 100% coverage. With no parameters to describe, the description adds no extra meaning but also does not need to. Baseline score of 4 is appropriate.
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 'Add a new automation rule' specifies a verb and resource, but is vague. It does not differentiate from sibling tools like 'update_automation_rule_in_account' or 'get_details_of_a_single_automation_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 is provided on when to use this tool versus other automation rule tools (update, delete, get). 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?
The description omits behavioral details such as whether the agent is permanently removed, any cascading effects, required permissions, or side effects. With no annotations, this is a significant gap for a delete 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 lacks important information. It is not overly verbose, but could be restructured to include more context 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 simplicity of the tool (one parameter, no output schema), the description is insufficient. It does not explain the impact of deletion, return behavior, or error states, 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?
Schema coverage is 100% and the parameter description (id: 'The ID of the agent to be deleted.') is clear. The tool description does not add further 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.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Remove' and the resource 'an Agent from Account'. It is specific enough to understand the tool's function, but does not differentiate from similar sibling tools like 'delete_an_account_agent_bot' or 'delete_agent_in_inbox'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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. The description is purely declarative without any 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 present, and the description does not disclose behavioral traits such as whether the deletion is reversible, permission requirements, or side effects (e.g., what happens to conversations assigned to the removed agent). The description solely restates the action without adding 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 concise sentence, but it essentially repeats the tool name in slightly different words ('Remove' instead of 'delete'). It is efficient but adds minimal value beyond the title.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 the tool's destructive nature (deleting agents from an inbox), the description should ideally mention return values (e.g., success confirmation) or conditions (e.g., agent must exist in inbox). The current description leaves significant gaps for an AI agent to safely 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 input schema already provides descriptions for both parameters (inbox_id and user_ids), achieving 100% coverage. The description adds no additional meaning beyond the schema, so it meets the baseline but does not 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 'Remove an Agent from Inbox' clearly identifies the action (remove) and resource (agent from inbox), and the tool name itself distinguishes it from siblings like 'delete_agent_from_account'. However, it does not explicitly differentiate from 'update_agents_in_inbox' or 'add_new_agent_to_inbox', leaving room for 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 'delete_agent_from_account' or 'delete_agent_in_team'. There is no mention of prerequisites (e.g., agent must be assigned to inbox) 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.
Behavior1/5
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 like permanence, prerequisites, side effects, or required permissions. For a deletion operation, 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 a single sentence with no wasted words. It is appropriately concise for a tool with no parameters.
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 severely lacking in context. It does not explain what an integration hook is, the implications of deletion, or any related data that might be affected. Given zero annotations and no output schema, the description should provide more 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 input schema has zero parameters, so the description does not need to add parameter information. The baseline is 4, and the description meets it by not adding unnecessary text.
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 ('Integration Hook'), making the purpose explicit. However, it does not differentiate from sibling tools like 'create_an_integration_hook' or 'update_an_integrations_hook'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 versus delete. The description simply states the action without 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, description must carry behavioral weight but only says 'List'. No disclosure of read-only nature, pagination behavior, 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?
Very short single sentence, which is concise but underinformative. Lacks necessary details to earn its place fully.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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. Missing info on what audit logs contain, pagination limits, or data format.
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 covers 100% of parameters (page), so baseline is 3. Description adds no extra meaning 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?
Description clearly states verb 'List' and resource 'Audit Logs in Account', but does not differentiate from sibling list tools like list_all_account_agent_bots or list_all_inboxes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 prerequisites or context for pagination.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 'Show', implying a read operation, but omits details like required permissions, whether the operation is safe (non-destructive), or what the response contains. This is insufficient for safe agent 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 extremely concise (one sentence) but lacks structure or additional useful information. While not verbose, it sacrifices completeness for brevity, making it minimally acceptable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 hints about return values or side effects. It does not, and the tool's purpose is vaguely defined, leaving the agent with insufficient context to determine if this is the right tool for the task.
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% (one parameter with description 'ID of the inbox'), so the schema already explains the parameter. The description adds no additional meaning or context beyond the schema, 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 'Show Inbox Agent Bot' uses a clear verb (Show) and resource (Inbox Agent Bot), indicating a retrieval operation. However, it does not explain what an inbox agent bot is or how it differs from similar tools like 'get_inbox' or 'update_agent_bot', limiting differentiation 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 is provided. There are no prerequisites, context hints, or when-not-to-use instructions, leaving the agent to infer usage from the tool 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 must disclose behavioral traits. It only says 'List all conversations' without mentioning whether it is read-only, requires authentication, has pagination, or any side effects. This leaves significant ambiguity about its 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?
The description is a single concise sentence with no extraneous words. However, it could have included qualifiers like 'for a contact' 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 lack of output schema and annotations, the description should clarify the scope (e.g., all conversations for a specific contact or across the account). It does not mention return format or pagination, leaving the agent underinformed.
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 schema, so the description does not need to clarify them. The description states the action (list) and resource (conversations), which suffices for a parameterless tool.
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 'List all conversations' clearly indicates the action and resource, but it lacks specificity. The tool name includes 'contact_conversations' suggesting scope per contact, yet the description omits this, making it indistinguishable from similar tools like 'list_all_conversations' or 'conversation_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 is given on when to use this tool versus its many siblings, such as 'get_single_conversation' or 'list_all_conversation_messages'. There are no context cues or alternatives 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 carries the full burden. It does not disclose behavioral traits such as idempotency, side effects, or whether it returns all labels across the account. The description is too minimal to 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (two words), but it omits important details like scope or return format. While brevity is good, it sacrifices completeness, 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 no annotations and no output schema, the description should provide more context about what is listed (e.g., all labels in the account). It is too sparse to be considered complete for a tool with these structural 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 schema has no parameters (0 params, 100% coverage). Baseline is 3 per rule for high schema coverage. The description adds no parameter-level meaning beyond the schema, but the schema already fully covers the absence of 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 'List all labels' clearly states a specific verb ('list') and resource ('all labels'), making it straightforward. However, it does not distinguish from sibling tools like 'list_all_labels_of_a_contact' or 'list_all_labels_of_a_conversation', missing specificity about the scope (e.g., account-level labels).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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, if the user wants labels for a specific contact or conversation, siblings exist but are not mentioned. The description lacks any usage 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 bears full responsibility for behavioral disclosure. The word 'update' implies mutation, but no details are given about side effects, idempotency, or required permissions. The empty input schema further obscures 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 (three words), but it lacks structure or front-loading. While it earns its place, it could be more informative without adding 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 tool has no parameters and no output schema, the description is incomplete. It does not explain how to identify the team to update or what fields are modifiable, leaving the agent with insufficient information to invoke 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?
Schema description coverage is 100% (no parameters), so baseline is 3. The description adds no information about parameters since there are none, but fails to clarify if the update relies on request body or other means.
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 a team' clearly states the verb 'update' and the resource 'team', distinguishing it from sibling tools like 'create_a_team' or 'get_details_of_a_single_team'. However, it lacks specificity about what fields can be updated, making it 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?
No guidance is provided on when to use this tool versus alternatives, such as 'update_agent_in_account' or other update tools. There are no prerequisites, exclusions, or contextual 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, so description must disclose behavioral traits. It fails to mention any effects, prerequisites, or constraints (e.g., whether duplicate responses are rejected).
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?
Extremely concise (one phrase), but could be more informative without sacrificing conciseness. Not structured with sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 no parameters, the description is adequate in addressing the core action, but lacks context about the account scope, typical usage, or related concepts.
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?
Input schema has zero parameters. The description does not add parameter details, but according to rules, baseline is 4 for zero 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?
Description clearly states verb 'Add' and resource 'canned response', but does not differentiate it from sibling tools like 'update_canned_response_in_account' or 'delete_canned_response_from_account'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 provide context or conditions 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?
Description does not disclose behavioral traits beyond the obvious deletion. No annotations provided, so the description carries full burden, but it lacks details on irreversibility, permissions, 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 is concise and front-loads the main action. However, it could be slightly 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?
While the tool is simple, the description lacks important context such as confirmation requirements, irreversibility, or ownership constraints. A more complete description would enhance agent 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?
No parameters exist, so schema coverage is 100%. Baseline score of 3 applies as description adds no additional parameter information, 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?
Description clearly states 'Delete a custom filter', which specifies the action (delete) and resource (custom filter). It's specific and distinguishable from siblings that perform other CRUD operations on filters.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_a_custom_filter' or 'list_all_filters'. It provides 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?
No annotations are present, so the description must disclose behavioral traits. It only says 'remove', which implies deletion but does not confirm irreversibility, permission requirements, or side effects (e.g., cascading deletions). This lack of detail 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no extraneous words. It efficiently conveys the core purpose, though it could benefit from slightly more detail 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 delete operation with a single parameter and no output schema, the description is mostly adequate. However, it omits any mention of success indicators, error conditions, or irreversibility, which would help the agent use the tool safely and effectively.
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 covers 100% of parameters, including a description for 'id'. The tool description adds no additional meaning beyond the schema, 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 'Remove' and the resource 'custom attribute from account', making the purpose evident. However, it does not differentiate from sibling tools like 'delete_agent_from_account' or 'update_custom_attribute_in_account', so it loses one point for lack of 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., updating the attribute instead of deleting it). There is no mention of prerequisites or context, leaving the agent 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?
With no annotations, the description must disclose behavioral traits. It only states the action without mentioning whether deletion is permanent, permissions required, or any side effects. The destructive nature is implied but 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 extremely concise at 4 words, with no wasted text. However, it may be too brief, lacking structure or additional context that could help the 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?
Given the tool has no parameters and no output schema, the description should provide complete context. It fails to specify which data source is targeted 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.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, so the description doesn't need to explain them. However, the description is ambiguous about what gets deleted (e.g., all data sources or a specific one), which reduces the baseline score from 4 to 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 'Delete a data source' clearly indicates the verb (delete) and resource (data source), distinguishing it from sibling tools like create, get, update. However, it lacks any scope or context about which data source is affected, which is slightly 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. There are no prerequisites, warnings about irreversibility, or examples of appropriate 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 does not state that this is a read-only operation or whether it has side effects. The minimal description leaves uncertainty about idempotency and 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 extremely concise—a single sentence. It is front-loaded with the key action and resource. However, the grammar is slightly awkward ('Get an agent bot details' could be 'Get details of an agent bot'), but overall efficiently communicates 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 zero parameters and no output schema, the description should clarify how the tool identifies which agent bot to retrieve. The context signals show no required parameters, suggesting an implicit identification, but this is not explained. The tool is incomplete for an agent to select correctly without additional 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 has zero parameters and 100% coverage. According to the rules, high schema coverage yields a baseline of 3. The description adds no further meaning beyond what the empty schema and tool name already imply.
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 an agent bot details' clearly states the verb 'get' and the resource 'agent bot details'. It distinguishes from sibling tools that operate on other entities (e.g., inboxes, contacts). However, it is slightly tautological as it repeats the tool name and lacks specificity about which agent bot 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?
No guidance is provided on when to use this tool versus alternatives like 'list_all_account_agent_bots' or 'update_an_account_agent_bot'. There is no mention of prerequisites or exclusions, leaving the agent to infer usage context from the tool 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 bears full burden. It only states the core function without disclosing any behavioral traits like permissions, rate limits, or side effects. For a reporting tool, 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 a single phrase, no wasted words. However, it is not a complete sentence and could be slightly more structured (e.g., 'Retrieves the count of outgoing messages grouped by the specified entity').
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 lacks information about the response format (e.g., object with counts per entity). Among many similar reporting tools, more context about the data structure and filtering 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 description coverage is 100% (the only parameter 'group_by' is fully described with enum). The description adds the term 'entity' which loosely maps to the parameter, but does not provide additional meaning beyond the schema. Baseline score of 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 tool retrieves outgoing messages count grouped by entity. The verb 'Get' and resource 'outgoing messages count' are specific. However, among many sibling reporting tools like 'get_channel_summary_report' or 'list_all_conversation_statistics', it does not 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 alternatives. With many reporting siblings, an agent needs context on what distinguishes this endpoint (e.g., it is a count aggregated by a specific entity, not a detailed breakdown).
Agents often have multiple tools that could apply. Explicit usage guidance like "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 solely carries the behavioral disclosure. It only states 'view', implying read-only, but does not mention any special permissions, rate limits, side effects, or data 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, concise sentence that front-loads the key verb and resource. No 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?
The tool has no output schema, but the description does not explain what the return value will be (e.g., policy details, structure). With zero parameters, the description should clarify how the policy is identified or what the response contains. 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.
Parameters3/5
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 does not add any meaning beyond the schema, but with no parameters, it fulfills the baseline. No additional insight into return values or usage context is provided.
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 'Xem một chính sách SLA' means 'View an SLA policy', which clearly states the action (view) and resource (SLA policy). It distinguishes from sibling tools like 'list_sla_policies', 'create_sla_policy', etc., by implying a single-policy retrieval. However, it is very minimal and lacks explicit 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. The description does not mention any 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?
The description does not disclose behavioral traits such as whether it returns all agents across teams or for a specific team. With no annotations, the agent has minimal clues about 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.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with only four words, but it lacks essential context about the tool's scope and usage. It earns a middling score because brevity comes at the cost of 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 minimal description, the tool lacks clarity on what exactly is returned. Sibling tools like 'get_account_agents' and 'get_details_of_a_single_team' overlap, and the description fails to distinguish them.
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 schema, so the description does not need to add much. However, it could clarify the scope (e.g., 'all teams' vs 'specific team'), but the absence of parameters makes the description 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 lists agents in a team. However, it does not differentiate from sibling tools like 'get_details_of_a_single_team' which may also list team members.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents 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. The description does not specify if a team selector is needed or how the tool determines which team to list agents from, especially given zero 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 mention any behavioral traits such as read-only, pagination, rate limits, or side effects. The word 'list' implies 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise and front-loaded, consisting of a single sentence. It efficiently conveys the basic 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?
For a simple list-all tool with no parameters and no output schema, the description is too minimal. It does not explain what CSAT survey responses are, what data is returned, or any constraints, leaving the agent without sufficient 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 has no parameters, and the schema description coverage is 100%. According to the rules, a baseline of 3 is appropriate since the description adds no parameter information 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 lists CSAT survey responses (in Vietnamese). The verb 'list' and the noun 'CSAT survey responses' provide a clear purpose. However, it does not differentiate from the sibling tool 'get_csat_survey_page'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 is no context about prerequisites, filtering, or when it's appropriate to use. The description lacks any usage 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?
No annotations are provided, and the description does not disclose any behavioral traits beyond the basic action. No information on side effects, authentication, or other behaviors.
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 a single sentence of three words. It 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?
Given the lack of annotations and no output schema, the description is insufficiently complete. It does not clarify differences from similar tools or provide context for a new conversation.
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 documentation is trivially complete. The description does not add extra meaning, but the baseline for zero params 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 'Create New Conversation' with a specific verb and resource. However, it does not distinguish from the sibling tool 'create_a_conversation', which appears to have the same 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 the similar 'create_a_conversation'. No context or exclusions 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, the description must convey behavioral traits. It only states that the tool runs a flow and that it does so in dry run mode by default. It does not disclose whether the action is reversible, what side effects occur in a dry run versus actual run, or any permissions needed. 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (6 words) and directly conveys the core action. However, it sacrifices necessary detail for brevity. It is front-loaded with the verb and resource, but additional context 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 zero parameters and no output schema, the description is incomplete. It does not explain what a 'flow' is, how the tool knows which flow to run, the difference between dry run and actual run, or what the outcome will be. For an action-oriented tool among many CRUD siblings, 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?
There are zero parameters, and schema coverage is trivially 100%. The description does not explain the absence of parameters, which may confuse an agent as to how the flow is identified. Baseline for 0 params is 4, but the lack of clarification reduces the score.
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 action 'Run a flow now' and notes the default behavior (dry run). The verb ('run') and resource ('flow') are specific, but it does not specify which flow is being run, assuming context. It distinguishes from sibling tools like list_scheduled_flows and create_scheduled_flow by focusing on immediate execution.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 mentions 'dry run by default' but does not explain how to perform an actual run or when a dry run is appropriate. No exclusions or prerequisites 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 carries full burden for behavioral disclosure. It states 'Update' implying mutation, but provides no details on required permissions, side effects, idempotency, or error conditions. 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 extremely concise at one sentence. It is front-loaded with the key action and resource, earning its place, but could benefit from additional structural elements like bullet points or examples.
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 lacks completeness by not specifying what attributes can be updated or if there are constraints on the 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?
Schema coverage is 100%, and the schema already describes the 'id' parameter as 'The ID of the agent to be updated.' The description adds no additional semantic information 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 'Update Agent in Account' clearly specifies the verb (update) and resource (agent in account), distinguishing it from sibling tools like add or delete. However, it does not elaborate on which fields can be updated, 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 usage guidelines are provided. The description does not indicate when this tool should be used versus alternatives like add_new_agent_to_account or delete_agent_from_account, nor does it specify 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 available, and the description does not disclose behavioral traits such as whether the update is idempotent, what fields can be changed, required permissions, or side effects. 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.
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 too brief to convey useful information beyond the basic action, making it minimally viable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 one-parameter tool with no output schema, the description fails to provide sufficient context about the update behavior or expected result. It lacks completeness even for a low-complexity 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 input schema fully describes the 'id' parameter, but the description adds no extra meaning. It does not explain what properties are being updated or how the update is performed. The schema coverage is 100% but the description provides no 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 'Update custom attribute in Account' clearly states the action (update) and the resource (custom attribute in an account). It distinguishes itself from sibling tools like add, get, delete, and get 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 is provided on when to use this tool versus alternatives like adding or deleting a custom attribute, or any preconditions or dependencies.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 indicates a create operation but lacks details on permissions, side effects, or idempotency. For a mutation tool, more disclosure 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 short sentence, front-loaded and concise. It earns its place, but could be slightly more descriptive 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 no parameters and no output schema, the description should clarify what a custom attribute is and how it is specified. The empty input schema raises questions, and the description does not resolve them.
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 baseline is 4. The description adds no extra meaning beyond the name, but it is adequate for a no-parameter 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 'Add a new custom attribute' is a clear verb+resource statement. The tool name specifies 'to account', but the description itself does not explicitly state the scope. However, it is distinct from siblings like 'add_new_agent_to_account'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 'update_custom_attribute_in_account' or 'delete_custom_attribute_from_account'. 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 carries the full burden. It only says 'Add a new portal', which implies creation but does not disclose side effects, authentication requirements, or what the default portal configuration looks like. 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.
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 also under-specified. While it is front-loaded, it does not provide additional context that would help the agent. It earns its place but could include a hint about the result or prerequisites.
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 params, no output schema), the description is minimally viable. However, it lacks completeness by not explaining what a portal is or what happens after creation. The sibling tools suggest a help center context, but this is not explicit.
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 100% coverage. With no parameters, the description adds no further meaning, but the baseline for zero params is 4. The description does not mislead and is adequate for a parameterless 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 'Add a new portal' clearly states the action and resource. It distinguishes itself from sibling tools like 'update_portal_to_account' and 'get_portal' by implying creation. However, it does not elaborate on what a 'portal' is in this context, which 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 is provided on when to use this tool versus alternatives. There is no mention of prerequisites, when not to use, or comparison to similar creation tools (e.g., 'add_new_category_to_account'). The agent is left 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 provided, the description must disclose behavioral traits. It only indicates a destructive action but does not clarify if deletion is soft/hard, reversible, or affects associated data. The absence of parameters implies reliance on context, which is not explained.
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 two words. While it avoids verbosity, it could benefit from additional context without losing conciseness. Scores high for minimalism 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 and annotations, the description is incomplete. It does not explain how the target contact is specified, what the result or return value is, or any side effects. For a deletion tool, more context is needed.
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 coverage is 100%. The description adds no parameter information, but there are none to describe. Per guidelines, baseline is 4 for 0 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 'Delete Contact' clearly states the verb and resource, making the tool's purpose obvious. However, it does not differentiate from sibling tools like contact_update or contact_merge, but the action is distinct 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 vs alternatives, nor any prerequisites or side effects. The agent is left without context on how to choose this over other contact-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 present, so the description carries the full burden. It implies a read operation (list) but does not disclose details like pagination, limits, ordering, or if results are filtered by some default scope. Without this, the agent may misjudge 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at two words, with no unnecessary information. It is front-loaded and easy to parse. However, the conciseness comes at the cost of missing context, but for dimension 5 it remains 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, the description should explain what is returned (e.g., list of contacts with fields, pagination info). It lacks this, leaving the agent without crucial information to process the response. The tool is simple but the description is too sparse.
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 the schema description coverage is 100% trivially. The description does not need to add parameter semantics, and the baseline for 0 parameters is 4. The description is adequate for this dimension.
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 'List Contacts' clearly states the action (list) and resource (contacts). It is specific and unambiguous. However, it does not differentiate from sibling tools like contact_search or contact_filter, which could perform similar operations with filtering capabilities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 contact_search, contact_filter, or contact_details. The agent cannot determine the appropriate context for using list vs. search/filter.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 gives no behavioral details beyond 'Get'. It does not state if it's read-only, requires permissions, or has 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 one short sentence with no wasted words. It is appropriately concise for a tool with no 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 that there are no parameters, no output schema, and no annotations, the description is adequate but does not explain what 'details' are included or the tool's role in the broader filter management workflow.
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?
According to the guidelines, zero parameters give a baseline of 4. The description adds no parameter information, but there is nothing to document, so it meets the baseline.
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 says 'Get a custom filter details', which is specific but fails to clarify how a 'single' filter is identified. The tool name implies fetching by ID, yet the input schema has no parameters, creating ambiguity about which filter is 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 like 'list_all_filters' or other filter tools. The description does not mention 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.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Fails to disclose safety, data freshness, auth needs, or return format. 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single concise sentence, no wasted words. Clearly 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 no output schema and many sibling reporting tools, description lacks detail on what statistics are included, how they are aggregated, and whether any filtering is needed. Incomplete for a reporting 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 exist, so schema coverage is 100%. Baseline for 0 params is 4, and description does not need to add parameter detail.
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 'Get conversation statistics grouped by inbox', which is a specific verb+resource. It differentiates from siblings by specifying grouping by inbox, though many reporting tools exist.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_all_conversation_statistics or get_channel_summary_report. No context on prerequisites or appropriate use cases.
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 is too minimal to disclose behavioral traits. However, the input schema's parameter descriptions partly compensate by stating that the mergee contact will be deleted. With no annotations, the description could have added more 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 extremely concise at two words, with no wasted text. However, 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?
Given the destructive nature of the operation (one contact deleted), the description lacks essential context about return values, error handling, and when to avoid use. No output schema or annotations exist to compensate.
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%, and the schema already describes both parameters fully. The description adds no extra meaning beyond the schema, meeting the baseline but not contributing additional 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 'Merge Contacts' is a clear verb+noun indicating the action and resource. It distinguishes from sibling tools like contact_update and contact_delete, but lacks specificity about the merge outcome.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 contact_update or contact_delete. The description does not provide context for when merging 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 available, and the description only states the action without disclosing consequences (e.g., irreversibility, required permissions, or impact on conversation).
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 at three words, with no unnecessary information. 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?
The description is too minimal for a delete operation. It does not explain how the message is identified (e.g., from context or previous calls), nor does it mention any side effects or output.
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, schema coverage is 100%. The description does not add parameter details, but baseline is appropriate since there are none to document.
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 'Delete a message' clearly states the action (delete) and resource (message), distinguishing it from sibling tools like create_a_message or update_a_message.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_a_message). The user might not know if deletion is permanent or reversible.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 user profile', omitting any details about side effects, authentication requirements, rate limits, or return format. This is insufficient for a tool with zero 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at two words, which is efficient. However, it could be slightly more informative without becoming verbose. It earns its place but doesn't add value beyond the name.
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 parameters, no output schema), the description is minimally adequate. However, it lacks context on what fields the profile contains, and among many sibling tools, a bit more specificity (e.g., 'current authenticated user') 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 input schema has no parameters (0 params), so schema coverage is 100%. The description adds no additional meaning but is consistent with the schema. According to guidelines, baseline is 4 for 0 parameters, and the description fulfills that 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 'Fetch user profile' clearly states the action (fetch) and resource (user profile), making the tool's purpose immediately understandable. However, among many sibling tools like 'get_account_details' and 'contact_details', 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 is provided on when to use this tool versus alternatives. There is no mention of whether it fetches the current user's profile or a specific user, nor any conditions 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 only states the action, with no additional behavioral context such as authentication needs, rate limits, or confirmation that this is a read-only operation (although implied by 'Get'). With no annotations, the description carries the full burden and 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, making it concise and front-loaded. However, it lacks structure or additional helpful information beyond the core 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?
Given the tool has no parameters, no output schema, and no annotations, the description is minimal. It communicates the basic action but does not describe the return value or what the layout entails, which could be useful for such a simple retrieval 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 tool has zero parameters, so schema coverage is 100%. The description does not need to add parameter information; the baseline for zero 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 states the verb 'Get' and the resource 'account branded email layout', clearly indicating the tool's purpose. However, it does not differentiate from the sibling tool 'update_account_branded_email_layout', missing an opportunity to clarify 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. Since a sibling tool exists for updating the layout, explicit usage context would be beneficial but is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 that this is a read-only operation, what data is returned, or any potential rate limits. The description is too 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 perfectly concise for a zero-parameter, straightforward 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 that there is no output schema, the description should explain what is returned (e.g., list of data source IDs and names). It only says 'list all data sources', which is incomplete for an agent to understand the output 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 no parameters, so the schema coverage is 100% and the description does not need to add parameter details. The description aligns with 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 (list) and resource (data sources). However, it does not specify the scope (e.g., all in account) or differentiate from similar tools like get_data_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 other data source tools (e.g., get_data_source for a single item). The sibling tools include multiple data source operations, but the description offers no contextual 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, so the description carries full responsibility for behavioral disclosure. It only states 'Write an automation state entry' without detailing side effects, required permissions, idempotency, or what happens on repeated writes. This is insufficient for safe tool selection.
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 easy to read. 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?
Despite having no parameters and no output schema, the description is too minimal. It fails to explain what an 'automation state entry' is, how it is identified, or what the tool actually accomplishes in the broader context of automation states. Sibling tools exist for retrieving and deleting states, so additional context is necessary for 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, so schema description coverage is 100%. According to the rubric, zero parameters have a baseline of 4. The description does not add parameter information because none exist, but it also does not explain how the state is determined (e.g., from context). Still, the score is appropriate given the 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 'Write an automation state entry' clearly specifies a verb and resource, indicating a write operation on an automation state. However, it does not distinguish between creating and updating, nor does it differentiate from sibling tools like 'claim_automation_state' or 'get_automation_state'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps 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. With siblings such as 'claim_automation_state', 'get_automation_state', and 'delete_automation_state', the description fails to explain the distinct use case for 'put_automation_state'.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 the basic action without disclosing effects like whether the agent is fully deleted or just removed from the team, reversibility, 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no wasted words, but it lacks necessary details for a complete understanding; concise but not fully informative.
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 purpose but omits behavioral context and side effects, leaving 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?
Only one parameter exists with 100% schema description coverage; the description does not add meaning beyond the schema, meeting 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 'Remove an Agent from Team' uses a specific verb and resource, clearly distinguishing it from sibling tools like 'delete_agent_from_account' and 'delete_agent_in_inbox'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 'update_agents_in_team' or 'delete_agent_from_account'; no 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 exist, and the description only states 'Remove' without disclosing behavioral details such as whether the deletion is permanent, if it requires specific permissions, 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the action. It is appropriately sized but 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.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple deletion tool with one parameter and no output schema, the description covers the basic action. However, it lacks behavioral context and usage guidance, making it minimally adequate.
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 100% with the 'id' parameter described as 'The ID of the automation rule to be deleted'. The description adds no new information beyond what the schema already provides, 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 'Remove' and the resource 'automation rule from account', which is specific and distinguishes it from sibling tools like 'add_new_automation_rule_to_account' or 'update_automation_rule_in_account'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 situations where other tools should be used instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 'Delete a webhook', which implies a destructive action but provides no details on reversibility, permissions, or impact on related data. With no annotations, more disclosure 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with only three words, no filler, and the purpose is front-loaded. 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?
With no parameters, output schema, or annotations, the description is minimally adequate but lacks context on which webhook is deleted and under what conditions it should be used.
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 the description cannot add parametric meaning. The baseline for 0 parameters is 4, and the description is clear about 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 states the verb 'Delete' and resource 'webhook', clearly indicating the operation. It distinguishes from sibling tools like create, update, list. However, it does not specify which webhook is deleted (no parameters), 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 vs alternatives such as create or update. No prerequisites or side effects 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 carries full burden. It states 'List' implying a read operation, but does not mention pagination, limits, or that it actually lists only one model type per call due to the required attribute_model parameter. The phrase 'all custom attributes' is slightly misleading.
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 and resource, making it 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 list tool with one required parameter, the description should mention that the parameter filters by attribute model. Without that, the agent may assume it lists all custom attributes unconditionally. No output schema exists, but the return format is not described either.
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%, so the input schema already documents the attribute_model parameter with enum and description. The description adds no extra meaning beyond 'custom attributes', and does not mention that the parameter is required or how it filters results. 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 'List all custom attributes in an account' clearly states the action (list), resource (custom attributes), and scope (in an account). It effectively distinguishes from sibling tools like add_new_custom_attribute_to_account or get_details_of_a_single_custom_attribute.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps 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_details_of_a_single_custom_attribute or when filtering by attribute_model is needed. No context 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?
No annotations are provided, so the description bears full burden. It implies mutation ('Claim') but does not disclose side effects, idempotency, authentication requirements, or what happens if the key is already claimed. The behavior is under-specified.
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, no redundancy. It is front-loaded with the core action and context. 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?
Given the lack of output schema and annotations, the description should explain what the tool returns (e.g., the claimed key) and any behavioral nuances. It fails to cover return value, error conditions, or concurrency behavior, making it incomplete for an agent to reliably 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?
There are zero parameters, so the schema covers everything. The description adds no parameter-specific meaning but also does not need to. 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 uses a specific verb ('Claim') and resource ('key'), and hints at a distinct purpose from sibling tools (locking for irreversible work). However, it does not explicitly differentiate itself from other automation state tools like put_automation_state or get_automation_state.
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 a clear context ('before doing irreversible work') but offers no guidance on when not to use this tool or which alternatives exist. It does not mention prerequisites or consequences of multiple claims.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 burden for behavioral disclosure. It only says 'Remove', implying destruction, but does not mention irreversibility, permissions, idempotency, or side effects, leaving the agent underinformed.
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 maximally concise while conveying the essential 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 deletion tool with one parameter and no output schema, the description is minimally adequate. However, given the large set of sibling tools and no annotations, additional guidance on behavior and usage 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?
Schema coverage is 100%, so baseline is 3. The description does not add any meaning beyond the schema; it merely restates that the id identifies the canned response. No additional constraints or format hints.
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 a Canned Response from Account' clearly states the verb (remove) and resource (canned response, scoped to account), distinguishing it from siblings like add_new_canned_response_to_account and update_canned_response_in_account.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 prerequisites or when to avoid deletion. The description lacks context for the agent to decide appropriately among 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 provided, so description must disclose behavioral traits. It only says 'Delete a scheduled flow' without mentioning permanence, side effects, permissions, 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?
Single sentence, concise and front-loaded. However, lacks any additional structure like examples or edge cases.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 parameters and no output schema, the description should explain consequences or requirements. It only repeats the tool name.
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?
Input schema has no parameters, so baseline is 4. Description adds no param 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 verb 'Delete' and resource 'scheduled flow', directly distinguishing it from sibling tools like create_scheduled_flow or update_scheduled_flow.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 (e.g., flow must exist, cannot be running). The description only states the action.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 only says 'List Agents in Account', implying a read-only operation, but no mention of authentication needs, rate limits, pagination, 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?
Single sentence, front-loaded, no wasted words. However, it might be too minimal; could have included more 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 no output schema or annotations, the description does not explain what the list contains (e.g., agent names, IDs, roles), or any scoping (e.g., agents for the current account only). Incomplete for a listing 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?
Input schema has no parameters (0 params), so schema coverage is 100%. Description adds no param info, but none is needed. 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 'List Agents in Account' clearly states the verb (List) and resource (Agents in Account). It distinguishes from sibling tools like 'list_all_account_agent_bots' (agent bots vs agents) and 'add_new_agent_to_account' (add vs 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 or when not to use this tool. With siblings like 'add_new_agent_to_account' and 'delete_agent_from_account', the purpose is implicit but not explicitly stated. No alternatives 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, and the description does not disclose behavior such as pagination, ordering, rate limits, or authentication requirements. It only states 'list all' without clarifying if results are returned in full or paginated.
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 (one sentence) with no fluff. However, it could include additional useful information without harming conciseness, such as return format 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?
The tool has no output schema and no annotations, so the description should provide more context about what is returned and how it behaves. It is incomplete for an agent to use effectively.
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 schema description coverage is trivially 100%. With 0 parameters, the baseline is 4, and the description does not need to add parameter information.
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 (automation rules), and scope (in an account). It distinguishes from sibling tools like get_details_of_a_single_automation_rule by implying a list 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., getting details of a single rule, adding/updating). The description does not mention when-not or provide context for selection.
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 such as pagination, authentication requirements, rate limits, or output format. The description carries the full burden in the absence of annotations but fails to add 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 sentence with no wasted words. It is appropriately sized for a simple tool with no 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?
The description is complete enough to convey the core purpose, but lacks details about the output or any limitations. Given no output schema, mentioning what is returned (e.g., list of team objects) 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?
There are no parameters, and the schema coverage is 100%. The description adds no parameter information, but since no parameters exist, it is not necessary. 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?
The description 'List all teams' is specific and unambiguous. It clearly states the verb (list) and resource (all teams), and distinguishes itself from sibling tools like 'get_details_of_a_single_team' or 'create_a_team'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 use cases, exclusions, or scenarios where other tools might 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?
With no annotations, the description must fully disclose behavior, but it only gives a high-level purpose. It omits details such as whether the data is aggregated over a time range, what statistics are included, or if it is a read-only 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, well-structured sentence that conveys the tool's core function 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?
Lacking output schema and annotations, the description should provide more context about the returned data structure and scope. The minimal description leaves significant ambiguity for a reporting 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 tool has zero parameters, so the description need not add parameter meaning. Baseline 4 applies per rubric for 0 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 retrieves conversation statistics grouped by channel type, distinguishing it from sibling summary reports that group by inbox, agent, team, or label.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 alternative reporting tools, 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 exist, and the description does not disclose behavioral traits like read-only nature, return format, or any side effects. The tool could be a read operation 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words, front-loading the key 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?
With no parameters, no output schema, and no annotations, the description is too brief. It does not explain the distribution format, time range, or how the data is grouped, which is needed for a reporting 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 tool has no parameters and schema coverage is 100%, meeting the baseline of 4. No additional parameter information 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 'Get first response time distribution by channel', which is a specific verb and resource, differentiating it from sibling tools like get_channel_summary_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 vs alternatives such as get_account_conversation_metrics or get_channel_summary_report. No context about prerequisites or scope.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 'List all portals,' implying a read operation, but fails to explicitly confirm read-only behavior, permissions required, or any limits. No additional behavioral traits are disclosed.
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 with the action and resource, making it efficient for an agent 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?
Despite having no parameters and no output schema, the description lacks context about return format, error handling, or limitations. An agent may not know what information is provided in the portal list, making it incomplete for decision-making.
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%. The baseline for 0 parameters is 4, and the description does not need to add parameter information. No issues.
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 ('portals'), and scope ('in an account'). It distinguishes this tool from siblings like add_new_portal_to_account and update_portal_to_account, as it is the only listing tool for portals.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 scenarios where it should be avoided or suggest other tools for related tasks, leaving the agent without 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 should disclose behavioral traits. It does not mention what statistics are included, time range, pagination, or any limitations. 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?
A single sentence with no redundancy. Every word is necessary 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 no output schema, no annotations, and many sibling reporting tools, the description is too brief. It fails to specify what statistics are included, time scope, or aggregation details, leaving the agent underinformed.
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 input schema is empty. The description adds meaning by stating the output is team-grouped statistics, which is 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.
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 conversation statistics grouped by team, which distinguishes it from siblings like get_agent_summary_report or get_account_conversation_metrics. It uses a specific verb and 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 over other reporting tools like get_channel_summary_report or list_all_conversation_statistics_summary. 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?
No annotations provided, so the description must carry the full burden. It only states the action without disclosing behavioral traits such as pagination, ordering, permissions, or that it is read-only. An agent gets minimal insight.
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 front-loaded. It is concise but does not waste words. However, 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 simplicity (no parameters, no output schema, no annotations), the description is minimally viable but lacks context about what 'custom filters' are, the expected response structure, or any caveats. Some additional context 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 input schema has zero parameters, so schema description coverage is 100%. The description adds no parameter details because none are needed, but it does not repeat schema content. According to guidelines, 0 parameters yields baseline 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 'List all custom filters' uses a specific verb ('List') and clearly identifies the resource ('custom filters'). It differentiates from sibling tools which perform CRUD on filters or list other 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 guidance on when to use this tool versus other list tools or filter-related tools. No context on prerequisites, alternatives, or exclusions. With many sibling tools, explicit usage guidance 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, so the description must disclose behavioral traits. It states it is a read operation (get), but does not discuss authentication requirements, data freshness, or any side effects. The minimal description adds limited transparency 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 sentence of five words, which is concise. However, it may be too brief to convey all necessary context, but it earns points for being front-loaded and not wasting 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 detail about what 'statistics' includes (e.g., counts, response times, satisfaction scores). Without an output schema, the agent cannot infer the output structure. This is incomplete for a tool that produces a report.
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 there is no parameter information to add. The description does not need to elaborate on parameters. With no parameters, the baseline is 4, and the description does not detract from that.
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 conversation statistics grouped by agent' clearly states the action (get), the subject (statistics), and the grouping dimension (by agent). It distinguishes this tool from sibling tools that group statistics by other entities such as channel, inbox, or team.
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 agent-level statistics but provides no explicit guidance on when to use this tool versus alternatives. Sibling tools like get_agent_conversation_metrics and list_all_conversation_statistics exist, but no comparisons 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, the description must disclose behavioral traits. It only states the action, omitting whether it is read-only, requires authentication, has rate limits, or returns detailed vs summary data. The name suggests 'details' but description lacks specifics.
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 redundancy. It is appropriately sized for a parameterless 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 no output schema and simple purpose, the description is minimal but sufficient to indicate the tool's basic function. However, it does not explain what 'details' are included, which would help the agent determine if this meets their needs.
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 the baseline is 4 per guidelines. The description adds no parameter-level detail, but since none exist, it is adequate. It does not detract from 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 'List all the Integrations' clearly states the verb (list) and resource (integrations), distinguishing it from sibling tools like create/update/delete integration hooks. It is explicit 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. There is no mention of prerequisites, context, or exclusions, leaving the agent to infer usage from context 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 for behavioral traits. It does not mention auth requirements, side effects, what happens if an inbox already exists, or any constraints. Only states the action without detailing 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 is front-loaded and contains no unnecessary words. 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 zero parameters and no output schema, the description is minimal. It lacks context about what inbox creation involves (e.g., default settings, required auth). It is adequate but not rich or informative 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 0 parameters (100% coverage), so no parameter information is needed. The description does not add extra meaning beyond the schema, but baseline for zero params is 4. It is sufficient for the parameter aspect.
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 an inbox' is a specific verb+resource that clearly distinguishes it from sibling tools like 'update_inbox' and 'list_all_inboxes'. It is unambiguous and directly states the tool's 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 vs alternatives, prerequisites, or when not to use it. The description offers no context for selection among 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 carries full burden. It does not disclose any behavioral traits such as pagination, ordering, or whether it is read-only. Only states 'List all inboxes', which implies a safe read operation but lacks explicit 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 and to the point.
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 minimal but adequate for a simple list operation. However, it lacks detail on what the response includes (e.g., full inbox objects or just names), which could be helpful 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 tool has zero parameters, and the schema coverage is 100% (no params). According to guidelines, 0 params yields a baseline of 4. The description adds no further parameter information, which is acceptable 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 'List all inboxes' is clear, using a specific verb 'List' and resource 'inboxes'. It distinguishes itself from the sibling tool 'get_details_of_a_inbox' which implies a single inbox 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 on when to use this tool vs alternatives. The description provides no context about 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?
No annotations are provided, so the description must disclose behavioral traits. It does not state that the operation is read-only, nor does it mention pagination, rate limits, or any side effects. The minimal description 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.
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 filler. 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 simple list operation with no parameters and no output schema, the description is minimally complete. It does not describe the return format or whether pagination is used, but the tool name implies it returns all webhooks.
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 100% schema description coverage. The baseline for no parameters is 4. The 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?
The description 'List all webhooks' clearly states the action (list) and resource (webhooks). It is specific and distinguishes from sibling tools that create, update, or delete webhooks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 or when alternatives might be preferred. While it is the only webhook listing tool, no context about prerequisites or typical use cases 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 are provided, so the description carries the full burden. It only states 'create', which implies a mutation, but no details about required permissions, side effects, or what happens on creation (e.g., default settings). This is insufficient for an agent to understand 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise phrase 'Create a team' with no wasted words. It is appropriately sized for a zero-parameter tool.
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 and no output schema, the description is sufficient to convey the operation. However, it lacks any context about what constitutes a team or any default behavior, which could be relevant.
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 description doesn't need to explain parameters. The baseline of 4 applies, and the description correctly indicates the tool creates a team without requiring additional 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 explicitly states the action 'Create' and the resource 'team', clearly distinguishing it from sibling tools like list_all_teams, get_details_of_a_single_team, update_a_team, and delete_a_team.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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., for team management). No prerequisites or context provided, 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 and the description omits any behavioral traits such as pagination, rate limits, or ordering. The tool's simplicity mitigates this somewhat, but transparency is 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?
Extremely concise single sentence. Front-loaded and to the point, but could benefit from minor additional context 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 tool with no parameters and no output schema, the description is minimal. It does not explain what AgentBots are, nor the format or scope of the result. Adequate but incomplete.
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 100%). The description does not need to add meaning, and no parameters are missing. Baseline 4 for 0 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 (list) and resource (AgentBots). It distinguishes from sibling tools like get_details_of_a_single_account_agent_bot, which retrieves a single bot.
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 guidance on when or when not to use this tool compared to alternatives. For a simple list, it's implied, but explicit differentiation would improve clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 'List all Canned Responses' but does not disclose behavioral traits such as authentication requirements, idempotency, pagination, or whether it is safe to call repeatedly.
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 and 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 minimal. It does not mention pagination, ordering, or the structure of the response, leaving gaps 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?
The input schema has 0 parameters, so schema coverage is 100%. Baseline for 0 parameters is 4; the description adds no parameter information, which is acceptable since there are none.
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 lists all canned responses in an account, using a specific verb (List) and resource (Canned Responses in an Account). It distinguishes itself from sibling tools that create, update, or delete canned responses.
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 read-only usage but lacks explicit guidance on when to use this tool vs alternatives like add or update. No mention of context or conditions for use.
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:

[![dmticket-mcp MCP server](https://glama.ai/mcp/servers/doanhnd9989/dmticket-mcp/badges/card.svg)](https://glama.ai/mcp/servers/doanhnd9989/dmticket-mcp)

Score Badge

Copy to your README.md:

[![dmticket-mcp MCP server](https://glama.ai/mcp/servers/doanhnd9989/dmticket-mcp/badges/score.svg)](https://glama.ai/mcp/servers/doanhnd9989/dmticket-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/doanhnd9989/dmticket-mcp'

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