Drin MCP Server

Server Quality Checklist

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

Latest release: v0.1.1
Disambiguation5/5
Each tool targets a distinct resource and action, even at 89 tools. The descriptions clearly separate overlapping operations like render_template (saved templates) and preview_template (drafts).
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern with snake_case (e.g., list_templates, create_campaign, send_email). No mixed conventions or vague verbs.
Tool Count2/5
89 tools is extremely high for an MCP server, likely overwhelming for agents. While the domain (email platform) is broad, the count far exceeds typical well-scoped servers (3-15 tools) and even the generous upper bound.
Completeness4/5
The tool surface covers nearly every aspect of the email platform: sending, receiving, templates, domains, contacts, campaigns, automations, webhooks, integrations, and more. Minor gaps like missing update_inbox or update_domain are negligible.
Average 3.9/5 across 89 of 89 tools scored. Lowest: 2.8/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 1 commit in the last 12 weeks
- Last stable release on July 27, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

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

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

How is the quality score calculated?

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

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

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

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

Tool Scores

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry behavioral disclosure. It does not mention authentication requirements, error handling, or any side effects. The description only states basic retrieval without additional behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that includes a parenthetical list of fields. It is concise and front-loaded, with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is adequate for a simple retrieval tool. It mentions the returned fields, which helps the agent understand the output, but does not describe the id format or provide context for the sender parameter.
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%, and the parameter descriptions in the schema are already informative. The tool description adds no extra semantic value beyond identifying that retrieval is 'by id', which is already implied by the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'preference topic', and the retrieval method 'by id'. It also lists the fields returned (name, slug, default subscription, visibility), making the purpose specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like list_topics. It does not mention prerequisites (e.g., needing the id) or conditions under which it 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?
Description implies a write operation ('Add'), but lacks details on permissions, duplicate handling, side effects (e.g., webhooks), or idempotency. No annotations provide additional safety cues.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words, but could slightly expand on behavior 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?
Tool has 6 parameters, nested objects, and no output schema. Description does not explain return values, behavior for existing contacts, or error cases, leaving gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 67%, with descriptions for 4 of 6 parameters. The description does not add any parameter-specific meaning beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Add), resource (contact), and scope (sender's address book), distinguishing it from sibling tools like update_contact and delete_contact.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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., import_contacts) or prerequisites like existence of sender. No exclusions or when-not-to-use indications.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 only says 'delete' without disclosing side effects like cascading deletions, reversibility, or required permissions. Minimal behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key action and resource. No wasted words, but lacks detail that could be added concisely.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations. For a destructive operation, missing information on permissions, reversibility, and error states makes it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and already explains both parameters (id, sender). The description adds no further meaning, so baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Uninstall (delete)' and the resource 'integration by id', distinguishing it from sibling tools like install_integration and update_integration.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 prerequisites (e.g., integration must be installed) or exclusions (e.g., cannot be undone).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of behavioral disclosure. It only mentions the partial update nature but does not disclose side effects, idempotency, authorization requirements, or what happens if the contact does not 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently conveys the core action and the critical 'partial update' behavior. No unnecessary words, fully front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters (including a nested object), no output schema, and no annotations, the description is far too sparse. It omits key contextual information such as what the response looks like, error handling, and constraints on parameters. It is not complete enough for agents to use effectively.
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 only 29% (2 of 7 parameters have descriptions). The tool description adds no parameter information beyond what the schema provides, failing to compensate for the low coverage. This leaves agents without guidance on fields like email, firstName, lastName, metadata, and subscribed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'a contact by id', and adds the specificity of 'partial — only provided fields change'. This distinguishes it from sibling tools like create_contact (create) and delete_contact (delete), making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies that this tool is used when modifying an existing contact and that only provided fields are changed, but it does not explicitly state when to use alternatives like create_contact for new contacts. It lacks explicit when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It mentions 'partial' update but does not explain whether the update is synchronous, permissions required, side effects (e.g., status change triggers), or how metadata is handled (merged vs replaced). This leaves significant gaps 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?
One sentence with key details efficiently front-loaded. While concise, the parenthetical listing of fields is clear and no unnecessary words are present. Slightly less structured than ideal but 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 7 parameters, no output schema, and nested objects (metadata), the description is insufficient. It lacks details on return values, error handling, merging behavior for metadata, and the role of the 'sender' parameter. Agents would have to infer too much.
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 43%. The description lists updatable fields and notes nullable types for senderId and defaultTemplateSlug, adding marginal value. However, it does not explain metadata constraints, the meaning of 'sender' beyond schema, or the format of defaultTemplateSlug. The compensation is partial.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'update' and the resource 'installed integration', specifies it is a partial update, and lists the modifiable fields (displayName, senderId, status, defaultTemplateSlug, metadata). This distinguishes it from related sibling tools like install_integration (create) and uninstall_integration (delete).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, prerequisites (e.g., existing integration ID), or exclusions. The description does not mention any conditions or context that would help an agent decide between this and other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states the creation action but does not mention side effects, permissions required, rate limits, or what happens if the address already exists. A mutation tool should disclose potential consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single, front-loaded sentence that efficiently communicates the core purpose. No fluff or redundant 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 having 4 parameters (2 required) and no output schema, the description does not explain return values or confirm what the agent should expect after creation. For a tool that creates a resource, the lack of output details leaves 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?
Parameter schema coverage is 100% with clear descriptions for each parameter (address, domainId, sender, displayName). The description adds minimal context ('so the agent can get replies') but doesn't clarify parameter specifics beyond what the schema provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Create a receive address' and the purpose 'so the agent can get replies and inbound mail.' It distinguishes from sibling tools like list_inboxes, get_inbox, and delete_inbox by specifying creation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. For example, it doesn't mention prerequisites (e.g., domain must be receiving-enabled) or when not to use it (e.g., when listing existing inboxes). Lacks context for agent decision making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states that it deletes, but lacks details on whether deletion is irreversible, required permissions, side effects like cascading deletions, 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. However, it is too brief and could include more useful information without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation with no output schema, the description is adequate but lacks completeness. It does not mention what happens upon success/failure, confirmation prompts, or related 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?
Schema description coverage is 100%, so the description adds no additional meaning beyond the schema. Baseline score 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 'Delete a webhook endpoint by id,' using a specific verb (delete) and resource (webhook endpoint). It effectively distinguishes from sibling tools like list_webhooks, get_webhook, create_webhook, and update_webhook.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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 when to prefer pause_automation or other delete operations. There are no prerequisites or context about when deletion is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only lists the returned metrics but does not disclose behavioral traits like read-only nature, rate limits, or required permissions. This is insufficient for a tool interacting with a tracking pipeline.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded with the main purpose and then lists the metrics. It is concise but could be improved by slightly better structuring (e.g., separating the list with a clearer break).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explicitly enumerates the returned metrics (dispatch counters and event counts), providing good context for what the agent can expect. It does not cover pagination or errors, but for a metrics endpoint this is reasonable.
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 already provides full coverage for both parameters. The description adds meaningful context for the optional 'sender' parameter, explaining its requirement for account-wide API keys, which goes beyond the schema's description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves campaign results with specific dispatch counters and event counts. However, it does not explicitly differentiate from the sibling 'get_metrics' tool, which might serve a similar role for 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?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or scenarios to avoid. The agent must infer usage from the tool name and sibling 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 must cover behavioral traits. It implies a read operation via 'list', but does not disclose authentication needs, rate limits, or whether the returned data includes full details or summaries.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence with 13 words, front-loaded with the main verb. Every word is necessary and no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list operation with one optional parameter and no output schema, the description adequately conveys the scope (catalog + installed). Minor gap: not stating if results are filtered or paginated, but acceptable for a straightforward 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 single optional parameter is fully documented in the schema. The description adds no additional meaning about the parameter, but schema coverage is 100%, meeting baseline expectations.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it lists the integration catalog and installed integrations, with examples. However, it does not explicitly distinguish from sibling list tools like list_template_gallery, but the verb 'list' with resource 'integrations' is specific 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 on when to use this tool versus alternatives such as get_integration or install_integration. The description lacks any context about preferred 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 bears full responsibility for behavioral disclosure. It only states the listing action, with no mention of side effects, authentication requirements, rate limits, or read-only nature. This is insufficient for a list operation with no existing annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It efficiently conveys the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a list tool with 3 parameters and no output schema, the description omits crucial context like pagination behavior, default ordering, or response structure. The schema hints at pagination via cursor, but the description does not explain this, 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?
With 100% schema coverage, the baseline is 3. The description does not add any parameter details beyond what the schema already provides, so no additional value is offered.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists 'reusable server-side email templates for the active sender,' using a specific verb and resource. This distinguishes it from siblings like get_template, create_template, or list_template_gallery, which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., list_template_gallery, get_template). There is no mention of prerequisites or exclusions, making it hard for an agent to choose correctly without additional knowledge.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that signing secrets are redacted, which is a key behavioral trait. However, with no annotations, it doesn't mention pagination behavior (though cursor parameter implies it), response structure, or any side effects. Adds some value but insufficient for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that front-loads the primary purpose and adds a critical detail (redacted secrets). Concise and efficient, but could be even more compact.
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?
Lacks output schema, so description should clarify return format (e.g., list of webhook objects). It only covers redaction. Adequate for a simple list operation, but incomplete for an agent to understand response structure.
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 parameters are fully documented in the schema. The description adds no extra meaning beyond the schema descriptions. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists webhook endpoints for the active sender, and adds a note about redacted secrets. It distinguishes from siblings like get_webhook (single) and create/update/delete, but could be more explicit about the resource type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use vs alternatives (e.g., get_webhook for a specific one). Usage is implied by the name and description, but no when-not 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; description only says 'Get', implying read operation but lacks details on error handling, auth requirements, 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise single sentence, front-loaded with key information. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple get-by-id tool, but lacks output description. No output schema, so description should clarify return 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 coverage is 100%, so schema already documents both parameters. Description adds no additional meaning beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get', resource 'address-book contact', and identifier 'by id'. Distinguishes from siblings like list_contacts and create_contact.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no prerequisites or 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 provided, so the description must fully disclose behavior. It mentions the types of suppressions and that sends are blocked, but does not address authorization requirements, pagination behavior (though cursor is in schema), or potential side effects. This is insufficient for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the primary action, and includes essential details (types, consequence) without extraneous information. Every word contributes value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of a list tool and the absence of an output schema, the description covers the main purpose and effect. However, it lacks information about pagination, filtering, or ordering, which would be valuable for an agent. It is adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers all three parameters (limit, cursor, sender) with descriptions. The tool description adds no further information about parameters, so it meets the baseline but 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.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists suppressed recipient addresses, specifies the types (hard bounces, complaints, manual, unsubscribes), and explains the consequence (sends blocked). This distinguishes it from related tools like add_suppression or list_contacts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives such as remove_suppression or add_suppression. The description only states what it does, without any context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses partial update behavior and the null clearing mechanism for description. However, it does not discuss permissions, validation, error handling, or what happens when updating non-existent topics, leaving gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. The first sentence front-loads the core purpose and the partial update nature. The second sentence adds a specific behavioral note. Efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters, no output schema, and a moderate complexity, the description is too brief. It covers only the partial update aspect and null handling for one parameter, but omits other behavioral details, error conditions, or expected outcomes like return value.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (43%), covering only id, sender, and description. The description only adds value for the description parameter (null clearing), which is already documented in the schema. Other parameters like name, slug, visible, and defaultSubscription receive no additional explanation, failing to compensate for low coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (update), resource (topic), and scope (by id). It specifies that updates are partial (only provided fields change), which distinguishes it from create_topic and delete_topic. The handling of null for description is also explicitly mentioned.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., topic must exist), nor does it exclude scenarios. Usage is implied but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "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 only indicates 'Get' (implying read-only) but lacks explicit disclosure of safety traits, authentication needs, or error behavior. The return format is specified but no further behavioral context is given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, precise sentence that conveys the tool's function without any extraneous words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately specifies the return format ({html, text}) and scope (archived at send/receive time). However, it omits details on error handling, permissions, and potential null returns, which 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 the parameter descriptions (id, sender) are already provided. The description adds no additional meaning 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.
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 the exact rendered HTML and text body of an archived message. It uses a specific verb 'Get' and resource 'rendered body', distinguishing it from sibling tools like get_email (metadata) or reply_email (sending).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_email or list_emails. There is no mention of prerequisites, restrictions, or exclusions, leaving the agent to infer the appropriate context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must cover behavioral traits. It states it retrieves by id but does not mention side effects, read-only nature, or any required permissions. 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?
Single concise sentence with no unnecessary words. Front-loaded with 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?
No output schema, so the description should indicate return value shape. It does not. As a simple get operation, it lacks completeness for an agent to understand expected output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for id and sender. The description only mentions 'by id', adding no additional meaning beyond what the schema provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get) and resource (one receive address/inbox by id). It distinguishes from siblings like list_inboxes (list all) and create_inbox/delete_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 alternatives, such as using list_inboxes to find an id first. 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.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses permanent deletion, but lacks details on idempotency, error behaviors, or side effects. With no annotations, the description carries the full burden and meets minimum expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no redundant words. Front-loaded with the core action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks explanation of return values, error cases, or idempotency. For a simple delete operation, the description is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema already provides descriptions for both parameters (id and sender) with 100% coverage. The description adds no additional meaning beyond what the schema offers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool permanently deletes a contact, using specific verb and resource. It distinguishes deletion from other contact operations like create, update, and unsubscribe.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like unsubscribe_contact. Does not mention 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?
With no annotations provided, the description carries the full burden. It covers purpose and a minor nuance, but omits behavioral traits like pagination details, rate limits, authentication requirements, ordering, or error handling. Given no annotation safety net, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise, front-loaded sentences with no wasted words. The first sentence defines purpose and output fields, the second adds a valuable detail. Efficient and scannable.
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 4 parameters, the description is adequate but lacks expected completeness for a list tool: it doesn't describe the return structure (beyond 'status + run counters'), pagination behavior, sorting, or error conditions. The pending approval detail is helpful but not sufficient.
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 baseline is 3. The description adds a nuance about draft automations with pendingApproval, but does not significantly enhance parameter meaning beyond the schema's own descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'list' and the resource 'automations (trigger→steps programs)', and distinguishes this from sibling tools like get_automation or create_automation. It also specifies returned fields (status + run counters) and filtering options, plus a special case (pending approval).
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 browsing automations with status filtering, but lacks explicit guidance on when not to use it or alternatives (e.g., 'use get_automation for a single automation'). The context suggests its role among siblings, but no exclusions are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description inadequately discloses behaviors. It mentions filtering but omits details like default output, pagination mechanics (beyond schema), sender determination, or whether results are ordered. A read operation carries little risk, but transparency is average.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, concise sentence that covers the core purpose and key filtering options. No extraneous words; every part is 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?
Lacks explanation of return format, pagination behavior beyond schema, or how it differs from sibling list tools. For a list operation with no output schema, more context would improve completeness. Adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so each parameter has a clear description. The tool description adds context ('active sender') and mentions two filters, but does not add significant meaning beyond what the schema already provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists address-book contacts for the active sender, with explicit filtering by subscribed state or free-text search. It distinguishes from siblings like get_contact, create_contact, and delete_contact, which target single records or mutations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select 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_contact or import_contacts. It does not specify prerequisites, default behavior, or exclusions, 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?
No annotations provided, so description carries full burden. It mentions listing for the active sender but lacks details on side effects, permissions, pagination, or default behavior. For a read operation, minimal behavioral disclosure is given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single, clear sentence with no unnecessary words. Efficiently conveys purpose and optional parameter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and lack of output schema, the description is minimally complete. It identifies the resource and filter but could clarify what 'active sender' means (e.g., default sender for API key).
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 100% description coverage, so baseline is 3. Description adds that domainId is an optional filter, but schema already states 'Filter to one domain.' No additional meaning beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool lists receive addresses (inboxes) for the active sender, with an optional filter. It distinguishes from sibling tools like create_inbox, get_inbox, delete_inbox by focusing on listing 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 Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description states the primary use case (list receive addresses) and optional filtering by domainId, but does not provide guidance on when to use this vs. alternatives like get_inbox or list_threads, nor does it mention when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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 it lists templates but does not disclose any behavioral traits such as read-only nature, authentication requirements, or potential side effects. Minimal transparency for a listing 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, concise sentence that front-loads the key action and result. Every word contributes meaning without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple listing tool with no output schema and missing annotations, the description covers the basic purpose but lacks details on return format, pagination, or safety. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single optional parameter 'sender', with a clear explanation in the schema. The tool 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.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it lists curated starter templates with specific content types (subject/html/text + sample data) and the action of copying into a new template. It distinguishes from sibling tool list_templates by specifying 'curated starter templates'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for getting starter templates to copy, but does not explicitly state when to use this tool versus alternatives like list_templates or create_template. No exclusion criteria or alternative options are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must reveal behavioral traits. It discloses partial update behavior and the special handling for description (explicit null to clear) and definition (wholesale replacement). However, it omits authorization needs, error conditions, and idempotency details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, dense sentence that front-loads the core action. Every phrase adds value with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters (one required, one nested object) and no output schema, the description covers the key update behavior but lacks details on return values, error handling, and prerequisites (e.g., segment existence). Additional context 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 60% (3 of 5 parameters have descriptions). The description adds value for the definition parameter by indicating wholesale replacement, and reinforces the description parameter's null semantics. It does not clarify the name parameter or provide additional structure for definition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (update) and resource (segment), and specifies it is a partial update. This distinguishes it from siblings like create_segment and delete_segment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is provided on when to use this tool versus alternatives (e.g., create_segment, delete_segment). The description focuses on behavior rather than usage context, leaving the agent to infer applicability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the campaign fallback behavior, but does not mention irreversibility, permissions, or failure modes. More detail would help.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise with two sentences; front-loaded with the main action. Could be slightly more structured, but no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and typical delete expectations, the description covers the primary effect and one key side effect. However, missing details on prerequisites or error handling make it complete but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds no additional meaning to parameters beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Delete) and resource (preference topic) with a specific side effect, distinguishing it from sibling tools like create_topic, update_topic, get_topic, or list_topics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives (e.g., updating topic status instead). The side effect on campaigns provides some context, but lacks recommendations or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the transparency burden. It discloses the batch limit and the structure of the emails array, but does not cover behavioral traits like atomicity, partial failures, error handling, 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences, front-loading the capacity limit, 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 complexity of a batch operation and no output schema, the description lacks essential details like response format, partial failure behavior, and error handling, 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.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds value by explaining that the emails array objects should be shaped like send_email without idempotencyKey/sender, which clarifies the parameter structure beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (send) and resource (emails) with a specific capacity limit (up to 100). It also distinguishes itself from the sibling tool send_email by indicating batch behavior.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps 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 implies use for sending multiple emails at once but does not explicitly state when to use this tool over send_email or other alternatives. No guidance on when not to use or prerequisites is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the mutation behavior (stamps unsubscribedAt) and the future send impact, but lacks details on idempotency, error states, or permissions. Adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one sentence with a parenthetical), front-loaded with the action, and contains no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple mutation tool with full schema coverage and no output schema, the description adequately covers the core behavior. It could mention return value or success state, but it's sufficient for selecting and invoking 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%, so baseline 3 is appropriate. The description does not add meaning beyond the schema for either parameter; the schema already describes 'id' and 'sender' sufficiently.
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 'Opt a contact out' with a specific verb and resource, and distinguishes it from siblings like resubscribe_contact by detailing the behavioral effect of stamping 'unsubscribedAt' and affecting future sends.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents 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 (e.g., resubscribe_contact, add_suppression). The context is implied by the action, but no exclusions or use cases are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It states the operation (list) and data returned (effective state), but lacks details on side effects, rate limits, authentication, or data volume. It does not explicitly label the tool as read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that is clear, front-loaded, and concise. Every word adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has 2 params, no output schema, no annotations. Description explains what it does but does not specify return format or possible values for effective state (e.g., subscribed/unsubscribed). Adequate but could be more complete for agent 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?
Schema coverage is 100%, so baseline is 3. Description adds semantic value beyond schema by explaining 'effective subscription state' as 'their explicit choice, else the topic's default', clarifying the meaning of the returned data. This justifies a score of 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it lists every topic of the sender for a specific contact, showing the effective subscription state (explicit choice or default). This specific verb+resource distinguishes it from siblings like list_topics (lists topics without contact state) and set_contact_topics (sets topics).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use or when not to use. The description implies use for checking a contact's subscription state per topic, but does not mention alternatives or exclusions. Sibling tools like set_contact_topics or list_topics are not referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It correctly indicates the tool returns subject, html, text, and variables, but does not mention side effects, safety, auth requirements, or error behavior. The description is basic but not 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, well-structured sentence that front-loads the key purpose and return fields. It avoids redundancy and is appropriately concise for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (2 params, no output schema), the description is minimally complete. It covers the core purpose and parameter usage but lacks context on return format, error handling, or prerequisites. Slightly sparse for full confidence.
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 schema already explains both parameters well. The description adds minimal extra meaning beyond summarizing the return fields and noting identification by id or slug, which is already in the schema. Baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and resource 'template', and specifies the returned fields (subject, html, text, variables). It also explains how to identify the template ('by id or slug'), distinguishing it from sibling tools like 'list_templates' and 'render_template'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description implies usage for retrieving a single template's content, but lacks direct comparisons or exclusion criteria. For a simple retrieval tool, this is adequate but not proactive.
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 adds one behavioral trait: the signing secret is redacted. However, without annotations, the description should disclose more about what happens (e.g., error on invalid id, return format). The single note is insufficient for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One short sentence with a parenthetical clarification. Front-loaded with verb and resource. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so description should hint at return structure. It only mentions the redacted secret, but fails to indicate other typical fields (e.g., URL, events). The description is adequate but incomplete for a GET 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?
Input schema already describes both parameters completely (100% coverage). The description adds no additional meaning beyond what the schema provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action 'Get', resource 'webhook endpoint', and scope 'one...by id'. Distinguishes from sibling tools like list_webhooks (which lists all) and other CRUD operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. Usage is implied (when you need details of a specific webhook), but no when-not or comparison with siblings is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden. It discloses that downloading bytes requires an authenticated GET on the url, but does not mention rate limits, permissions, or error handling for invalid ids.
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, consisting of two sentences that are front-loaded with the main purpose and followed by a key behavioral note. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and lack of output schema, the description covers the basic functionality but misses details about the structure of the returned metadata (e.g., fields like filename, size) and how to handle empty results or errors.
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 description does not add any additional meaning to the parameters beyond what the schema already provides. The baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'List attachment metadata for a message.' It uses a specific verb ('list') and resource ('attachment metadata'), and distinguishes itself from siblings like list_emails or get_email by focusing on attachments.
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 (requires a message id) but provides no explicit guidance on when to use this tool versus alternatives, no exclusions, and no mention of prerequisites (e.g., needing a message id from get_email).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description partially discloses behavior by noting 'for the active sender' and implying sender parameter usage. However, it does not mention pagination, list size limits, default ordering, or other behavioral traits. Some transparency but 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no redundancy. It immediately states the action and key details, earning its place without fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not mention the return format (e.g., paginated array of segments with cursor) despite lacking an output schema. Given the parameter count and schema coverage, it is minimally adequate but lacks completeness for a list 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 all three parameters are described in the schema. The description adds no additional parameter-level context beyond what the schema already provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists saved audience segments, specifying they are declarative filters over contacts and scoped to the active sender. It distinguishes from sibling tools like list_contacts (lists contacts) and get_segment (single segment).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when you need to list segments but provides no explicit guidance on when to use this versus alternatives like list_contacts or get_segment. No when-not-to-use or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description provides good detail on state transition: returns to lane it was paused from and continues dispatch. However, lacks information on permissions, error conditions, and idempotency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key information. No redundancy; every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so return value is not described. For a mutation tool, mentioning what is returned would be helpful. Missing prerequisites and error cases. Partially complete but leaves 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?
Schema coverage is 100%—both parameters are described. The description adds no new meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb and resource: 'Resume a paused campaign'. Distinguishes from siblings like pause_campaign, and explains the lane behavior (sending or scheduled) which adds 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 explicit guidance on when to use this tool versus alternatives (e.g., send_campaign, approve_campaign). Does not mention prerequisites (campaign must be paused) 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?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns DNS records, but does not mention prerequisites (domain ownership), idempotency, whether overwriting occurs, or any side effects. For a mutation operation, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences (15 words), front-loads the action and the key output. Every word adds value; no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple add tool with two well-documented parameters, the description covers the core action and return value. It lacks context on prerequisites, limits, or the role of the sender parameter, but these are partially covered by the schema. Overall, fairly complete given the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the parameter descriptions in the schema are adequate. The description does not add any additional meaning beyond what the schema provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add a sending domain') and the resource, and distinguishes from siblings like verify_domain or delete_domain by noting it returns DNS records for verification. No ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is the first step for adding a domain, and that DNS records must be published afterward. However, it does not explicitly state when not to use it (e.g., if domain already exists) or compare to alternatives like list_domains or get_domain. Still, the context is clear enough for typical use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It discloses a key side effect: 'Sends that reference it will then fail.' However, it does not mention irreversibility or other behavioral details, making it adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short, front-loaded sentences: first states action, second adds a key consequence. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool, the description covers the primary action and a notable side effect. It could mention irreversibility, but overall it is fairly complete. No output schema exists, but return value is not critical.
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 both parameters. The description's mention of 'by id or slug' aligns with the id parameter but does not add new meaning beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete) and the resource (saved template) with identifier method (by id or slug). It distinguishes from sibling tools that list, get, render, create, or update templates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (when you want to delete a template) but does not explicitly guide when to use versus alternatives. No when-not-to-use context is provided, though the consequence of failing sends is mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It describes what data is returned but does not explicitly state that the operation is read-only and has no side effects, which is expected for a get tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently front-loads the purpose and lists relevant fields with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately covers return fields. Parameter coverage is complete via schema. However, it could mention the optionality of the sender parameter or any prerequisites, which are minor 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?
Schema coverage is 100%, so baseline is 3. The description mentions 'by id' but the schema already describes the id parameter as 'Automation id.' The description adds no additional semantic value beyond the schema for either parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a single automation by ID and lists the specific fields returned (trigger, step program, status, pendingApproval flag, counters), distinguishing it from list_automations which returns multiple automations.
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 fetching a specific automation's details, but does not explicitly state when to use this over list_automations or other siblings, nor provide any exclusion or alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description adds context about DNS records and verification state, but does not explicitly state that it is a read-only operation or mention authentication requirements or rate limits. Adequate for a simple read tool but lacks full behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Front-loaded with the verb and resource. Excellent conciseness.
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?
Tool is simple with two parameters (schema covers both) and no output schema. Description explains what is returned (DNS records and verification state). Fully adequate for the tool's complexity, though could mention return format or pagination if applicable.
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 description adds minimal value beyond the schema ('by id' matches the id parameter). Baseline score of 3 is appropriate given high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Get a domain by id' and specifies what is included (DNS records and verification state). It distinguishes from sibling tools like list_domains, delete_domain, verify_domain.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool over alternatives. The description implies usage for retrieving a specific domain's details, but does not mention exclusions or provide context for when to use other domain-related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It correctly implies a read-only, non-destructive operation and hints at the return value (MX records). However, it omits details on authorization requirements or potential side effects (though 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?
A single, well-structured sentence that conveys the core function without extraneous words. Front-loads the verb and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with two parameters and no output schema, the description adequately covers the purpose and primary output. It could mention idempotency or safe-to-call nature, but is sufficient.
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 baseline is 3. The description does not add any additional meaning beyond the schema; it restates the purpose but provides no extra parameter-level details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Read') and the resource ('domain's inbound-receiving state and the MX record(s)'). It distinguishes from siblings like set_domain_receiving (write) and get_domain (general domain info).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as set_domain_receiving or verify_domain. It lacks explicit usage context 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.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds the behavioral detail 'secrets redacted', which is useful. However, with no annotations, it does not disclose whether the operation is read-only, authentication requirements, or any side effects. The tool is likely a safe read, but more transparency would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It efficiently communicates the core action and a notable behavior (secrets redacted).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-id operation with no output schema, the description is adequately complete. It could mention that the response includes integration details minus secrets, but the current description is sufficient for basic 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 coverage is 100%, so the schema fully describes both parameters. The description adds no additional meaning beyond 'by id' matching the required 'id' parameter. Baseline 3 for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'one installed integration by id', distinguishing it from sibling tools like list_integrations, install_integration, etc. The purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when retrieving a single integration by id, but does not explicitly mention alternatives (e.g., list_integrations for listing all) or when not to use this tool. No prerequisites or decision context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the burden of behavioral disclosure. It indicates the tool returns segment details, which implies a read-only operation, but does not mention error handling, authorization requirements, or response format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It is front-loaded with the main action and includes a brief example of what is returned.
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's simplicity (a get-by-id operation) and lack of output schema, the description is mostly complete. It specifies the key contents of the response (match and conditions) but could be improved by noting other potential fields or pagination.
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% (both parameters have descriptions in the schema). The description adds 'including its { match, conditions[] } definition' which provides context about the response but not additional meaning for the parameters themselves.
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 one segment by id', specifying the verb and resource. It further details what is included ('match, conditions[] definition'), distinguishing it from other segment tools like list_segments or create_segment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives (e.g., preview_segment). The description is straightforward but lacks context on when it is appropriate to use this tool over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the scope (one automation) and returned fields (status, step, trigger context, next wake time). However, it does not mention potential side effects, rate limits, or data volume. Adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded with the core action and includes relevant details (returned fields). Every word earns its place; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description compensates by listing the returned fields (status, current step, trigger context, next wake time). It mentions per-contact runs and pagination is implied via schema. Nearly complete for a list 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 description coverage is 100%, so the schema already documents all 5 parameters. The tool description adds no additional meaning beyond what the schema provides. 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 'List', the resource 'one automation's runs', and the scope 'one automation'. It distinguishes from sibling tools like list_automations and get_automation by specifying it returns per-contact run details.
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 (list runs for a specific automation) but does not explicitly state when to use this tool versus alternatives (e.g., get_automation for settings, list_automations for all automations). No prerequisites or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits like rate limits, authentication requirements, or what happens when no results are found. It only states ordering and filtering, leaving gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the main action and key features. Every word earns its place with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a list tool with 6 well-documented parameters, the description covers ordering and filtering. However, it omits mention of pagination (cursor parameter) and the default/max limit, which are important for usage 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 description coverage is 100%, so the schema already documents all parameters. The description adds minimal new meaning beyond restating filtering options. 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.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List', the resource 'sent and received messages', ordering 'most recent first', and filtering by 'direction/status/search'. It is specific and distinguishes from sibling tools like get_email or list_threads.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for listing messages with filtering options. It does not explicitly state when not to use or alternatives, but the context of siblings provides some guidance. It is clear enough for most agents.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description adds ordering (most recent first) and thread composition (inbound+outbound joined). Does not explain pagination or cursor behavior beyond schema. Adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with main action, no filler. Every word adds value.
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?
Schema covers all parameters. Description adds scope (both directions, sorting) missing from schema. Lacks mention of pagination semantics but sufficient for a list tool with well-defined schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% already. Description only echoes 'filter by inboxId' from schema, adding no new semantics. 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?
Clearly states it lists conversation threads (inbound+outbound joined, most recent first) and can filter by inboxId. Distinguishes from siblings like list_emails and get_thread.
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?
Implied usage: use to list threads. No explicit when-to-use, when-not, or alternatives among many sibling tools. The filtering by inboxId is mentioned, but no guidance on pagination or comparing with other list tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description adds context about topics being used for opt-in/out and visible on a public page, but does not disclose authorization needs, rate limits, or guarantee it's 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?
Two sentences, front-loaded with the action and examples, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple listing tool with fully described parameters, the description is fairly complete, mentioning the public preferences page. Lacks output schema info but acceptable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter described. The description does not add significant meaning beyond the schema; it mentions 'active sender' but does not elaborate on the sender parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'marketing preference topics' with concrete examples. It distinguishes from sibling tools like get_topic (single topic) and create/update/delete mutations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for listing all topics for the active sender but does not explicitly state when to use this vs. alternatives like get_topic or set_contact_topics.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses mutation (remove) but lacks details on prerequisites, side effects, or behavior for non-suppressed addresses. No annotations provided.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with verb and object, efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Simple tool with two well-described parameters; description covers the core action, though could mention idempotency or response. Mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, description adds no extra meaning beyond schema descriptions for email and sender parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it removes an address from the suppression list, specifying the effect (can be emailed again). This distinguishes it from siblings like list_suppressions and add_suppression.
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?
Implies usage for re-enabling email delivery after suppression, but no explicit guidance on when to use vs alternatives 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.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing behavior. It mentions that enabling returns MX records, but does not disclose side effects like whether disabling drops existing mail, or if changes are immediate/reversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences, front-loaded with the action, and contains no redundant information. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple toggle tool with well-defined parameters and no output schema, the description covers the main purpose and notable behavior (MX records). It lacks detail on disabling behavior but is 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% (all parameters described in schema). The tool description adds no further meaning beyond what the schema already provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Enable or disable inbound receiving on a domain.' It also adds a specific detail about returning MX records when enabling, which distinguishes it from related tools like get_domain_receiving.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is used to change receiving settings but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives like get_domain_receiving for checking current state.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses partial update and clearing of html/text via null, which is helpful beyond schema. However, no annotations exist, and description omits details like required permissions, idempotency, error states, or whether clearing other fields (name, slug, etc.) is possible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences front-loaded with key behavior and special case. No fluff; efficient and scannable.
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?
With 7 params, no output schema, and no annotations, the description covers core update behavior and null handling. Could benefit from mentioning response expectations or immutable fields, but overall adequate for a mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 57% (4/7 params have descriptions). Description adds value by explaining partial update and null handling for html/text, but does not elaborate on name, slug, or subject beyond minimal schema info. Baseline 3 adjusted slightly due to partial compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool updates a saved template by id or slug, specifies partial update behavior, and highlights null clearing for html and text. This distinguishes it from sibling tools like create_template, delete_template, and get_template.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage context for updating templates but lacks explicit guidance on when to use vs alternatives (e.g., create_template) or when not to use (e.g., read-only operations). No exclusion criteria provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full burden. It correctly implies a read operation and indicates polling behavior, but lacks details on authorization, rate limits, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose. Efficient but could be slightly improved by separating the polling advice into a distinct statement.
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's simplicity (2 params, no output schema, no annotations), the description adequately covers purpose, return data, and a usage hint. It is complete for a read operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds no parameter-specific details beyond the schema; it merely reiterates 'by id' and lists return fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (get one campaign by id) and lists the scope of returned data (status, audience refs, content, schedule, live counters), effectively distinguishing it from siblings like list_campaigns or get_campaign_metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly suggests polling for send progress, giving a clear use case. While it does not define when not to use or name alternatives, the context is sufficiently clear for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses ordering (oldest→newest), scope (header + all messages both directions), but lacks info on pagination, auth requirements, or rate limits. It does not contradict any annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no fluff, front-loaded with the core action. Every word adds value, making it concise and well-structured.
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 provides the high-level output (header + messages ordered) but lacks detail on the return structure, e.g., message fields or thread metadata. Given the tool's simplicity (2 params), the description is adequate but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the description adds no new meaning beyond the parameter descriptions in the schema. The description does not elaborate on 'id' or 'sender' beyond what's already stated. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a full conversation with header and all messages, ordered oldest to newest, and includes both directions. This distinguishes it from siblings like list_threads (presumably lists thread summaries) and get_email (single message).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving a complete thread but does not explicitly state when to use this tool over alternatives like list_threads or get_email. No when-not-to-use guidance or exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses return types for both webhook and OAuth providers, but does not mention side effects, idempotency, permissions, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the main purpose, and contains no unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the description explains return values well given no output schema, it lacks details on error conditions, prerequisites, or idempotency, leaving some gaps for a tool with 6 parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. The description adds context about `from` being required for webhook-kind and `provider` referencing the catalog, but does not elaborate on other parameters beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Install an integration by `provider`' and explains the differences between webhook and OAuth kinds, distinguishing it from siblings like list_integrations or uninstall_integration.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context for when to use (installing integrations) and mentions the requirement for `from` in webhook-kind providers, but does not explicitly state when not to use or suggest alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses the return format (full updated effective-state list) but lacks details on idempotency, side effects, authorization needs, or whether it overrides or merges previous states.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: the first states the purpose succinctly, the second details the topics parameter and return value. No wasted words, front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core operation and return, but given the lack of output schema and annotations, it omits error scenarios, prerequisites (e.g., contact existence), and potential side effects, leaving some gaps for a mutation 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?
Schema coverage is 100%, but the description adds meaningful context: it provides an example of the topics list structure, explains the state enum values, and clarifies that the full updated list is returned, which goes beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the verb 'Set' and the resource 'contact's per-topic subscription states', clearly distinguishing it from sibling tools like get_contact_topics (retrieves) and bulk unsubscribe/resubscribe.
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 granular per-topic control but provides no explicit guidance on when to use this tool versus alternatives (e.g., unsubscribe_contact, resubscribe_contact) or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explicitly states that the address 'can never be emailed', clearly indicating an irreversible destructive action. This compensates for the lack of annotations. However, it does not detail permissions or side effects beyond the result.
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 (13 words) that front-loads the purpose and example. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 params, no output schema), the description adequately covers the core functionality. It could mention the absence of a return value or error scenarios, but it is complete enough for selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The tool description does not add additional meaning beyond the schema definitions, though the schema itself is descriptive enough.
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 'suppress an address' and its consequence 'so it can never be emailed', with an example 'opt-out request'. It distinguishes this tool from siblings like list_suppressions and remove_suppression.
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 use case (opt-out request) but does not explicitly state when to use this tool versus alternatives like unsubscribe_contact, or mention any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It notes that the template is reusable, server-side, and uses Handlebars subset, and that slug must be unique per sender. It does not discuss auth requirements, side effects, or error conditions, which is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with purpose, and contains no extraneous information. Every sentence adds value.
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 high schema coverage and no output schema, the description covers the creation process, required fields, template language, and slug behavior. It does not mention return value or error handling, but for a creation tool with no output schema, it is reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds value by stating that 'subject and at least one of html/text are required' (schema only lists subject as required) and that slug defaults to slugified name. This clarifies usage beyond schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a reusable server-side template,' using a specific verb and resource. It distinguishes from siblings like update_template, delete_template, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions required fields (subject and html/text) and slug uniqueness, but does not provide explicit when-to-use or when-not-to-use guidance compared to other template-related tools like render_template or send_email.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It explains the defaultSubscription behavior but does not mention any side effects, return values, or required permissions. The description adds some value beyond the schema but has gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the purpose, and every sentence adds value. There is no unnecessary text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence 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 6 parameters and no output schema, the description is incomplete. It does not mention what the tool returns (e.g., created topic ID), error conditions, or creation side effects. A creation tool should provide more context for successful 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?
Schema description coverage is 100% (all 6 parameters documented). The description adds contextual meaning for defaultSubscription ('what a contact without an explicit choice counts as'), which enhances understanding. For the remaining parameters, the schema suffices.
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 'Create a preference topic' with a specific verb and resource. It distinguishes the tool from siblings by explaining its unique purpose: contacts can opt in/out independently of global subscription, and campaigns can target it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool (create a new preference topic) and explains the key parameter defaultSubscription. However, it lacks explicit when-not or alternative guidance, such as specifying update_topic for modifications.
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?
Without annotations, the description carries the burden. It discloses the 409 refusal and hints at destructive nature ('tear down its identity'), but lacks details on side effects (e.g., cascading deletions) or success response. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise, front-loaded sentences with no fluff. Every word adds value: action, scope, and a key constraint.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete operation, the description covers primary purpose and a critical precondition. However, success behavior (e.g., response format) is omitted, and the lack of behavioral annotations means the description could do more. Still mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters with descriptions. The description adds no extra parameter meaning beyond the schema. Per guidelines, 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?
Clearly states the action ('Delete a sending domain') and resource, distinguishing it from sibling tools like add_domain or get_domain. Includes a specific error condition (409 when inboxes exist), reinforcing 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 Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly indicates when to use (to delete a domain) and a constraint (domain must have no inboxes). However, it does not mention alternatives or when not to use, leaving some ambiguity for agents unfamiliar with the domain lifecycle.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries the full burden. It correctly identifies the tool as a read operation (get) and lists the returned fields. However, it does not disclose any behavioral aspects such as authentication requirements, rate limits, or potential side effects. The description is adequate but adds no extra behavioral context beyond the name and schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that immediately states the purpose and key outputs. No unnecessary words; every part contributes meaning. Excellent front-loading and conciseness.
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 there is no output schema, the description provides a good overview of the return data (recipients, status, lifecycle events, attachments). It does not detail the structure or format, but for a simple get operation this is sufficient. The presence of sibling tools like get_email_body shows it covers more than they do.
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 both parameters (id, sender) are documented in the schema. The description does not add any additional meaning or context for the parameters beyond what the schema already provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with 'Get one message's full detail', which clearly specifies a read operation with a specific resource (one message). It distinguishes from sibling tools like list_emails (list), get_email_body (partial), and list_email_attachments (attachments only) by listing the exact fields returned: recipients, status, lifecycle events, attachments.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when full details of a single message are needed, but does not explicitly state when to use alternatives like get_email_body or list_email_attachments. The context from sibling tools makes the use case clear, but explicit exclusions or when-not-to-use guidance is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden. It correctly implies a read operation and describes the data returned. However, it does not explicitly state that it is non-destructive or indicate any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that lists the resource and scope upfront. It contains no extraneous words and efficiently communicates the tool's function.
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's simplicity (3 optional parameters, no output schema), the description provides a reasonable outline of the return values (totals and daily series). It could be slightly improved by noting the response format, but is largely sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all three parameters (100% coverage). The description adds minimal extra value beyond summarizing the date bounds. The sender parameter is not elaborated beyond what the schema states.
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 lists the specific metric types (send, delivery, bounce, complaint, open, click) and indicates both totals and daily series. It implicitly distinguishes from sibling tools like get_campaign_metrics by focusing on aggregate, not campaign-specific, metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states the optional date bounding, giving context for when to use the from/to parameters. However, it does not provide explicit guidance on when to prefer this tool over siblings, such as get_campaign_metrics or list_emails.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description mentions ordering ('newest first') and account-wide scope but does not disclose rate limits, required permissions, side effects, or pagination behavior beyond cursor usage. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: the first clearly states core purpose and sorting; the second distinguishes from sibling. No wasted words, front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 6 parameters and no output schema, the description covers purpose and usage distinction well. However, it omits details on return format, pagination mechanics (beyond mentioning cursor), and error scenarios, leaving some gaps for effective invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all 6 parameters. The description adds no additional parameter-level meaning; it only mentions 'account-wide key' in relation to the sender parameter, which is already clear from schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool lists messages across all products account-wide, sorted newest first. It explicitly contrasts with list_emails, making the scope unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description provides guidance on when to use this tool vs list_emails: 'Like list_emails but not scoped to one sender — use an account-wide key'. It implies usage context but lacks explicit when-not-to-use or alternative tools for other cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that secrets are never returned and internal service keys are hidden, which are key behavioral traits. However, it does not mention pagination behavior or that it is a read-only operation (though implied).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence with a parenthetical note. No wasted words, directly states purpose and two key caveats. Ideal conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a listing tool with no output schema, the description covers the main purpose and caveats. It assumes the agent knows return format and that no parameters are required (though true). Missing details about default limit or pagination, but overall 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 coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema for any parameter. It does not explain 'sender' or 'cursor' further.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it lists active API keys for the account, with specific behaviors (secrets never included, internal keys hidden). This clearly distinguishes it from siblings like create_api_key or revoke_api_key.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives. While the purpose implies listing versus creating/revoking, there is no direct guidance such as 'use this to view keys, not to manage them'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It mentions listing and verification status but does not disclose if it's read-only, any side effects, or pagination behavior. Basic disclosure but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first states purpose, second gives a usage tip. No extraneous words, front-loaded with key action. Every sentence is necessary and clear.
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?
Adequately covers purpose and filtering hint. No output schema, but description implies return of domains with verification status. Could briefly mention typical use case (e.g., validating domain setup) but is complete enough for a simple list 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 parameter descriptions. The description adds extra context for the 'status' parameter (e.g., 'verified' gives sendable domains). Baseline 3 is appropriate as description adds marginal value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it lists sending domains and their verification status, using a specific verb+resource. It distinguishes from sibling tools like get_domain (single domain) and add_domain/verify_domain (mutations).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to use the status parameter ('Pass status=verified to get only sendable domains'). Provides clear context for filtering, though does not explicitly compare with alternatives. Since sibling tools are distinct, this is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It states 'no save, no send' and 'UNSAVED template draft,' clarifying non-destructive behavior and working on unsaved data. It does not mention permissions, rate limits, or error handling, but is adequate for a preview tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with action and output, then use case. Every word adds value, no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters, no output schema, and low schema coverage, the description is insufficient. It does not explain parameter interactions, default behavior for missing parameters, or return format. However, as a preview tool, basic completeness is achieved, but gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (40%), and the description adds no parameter-specific details beyond mentioning 'merge data' for the data parameter. The roles of html, text, subject, and sender are explained only in the schema, not in the description, leaving ambiguity for the agent.
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 renders an unsaved template draft with merge data and returns the result without saving or sending. It explicitly distinguishes from create_template and other template operations. The verb 'Render' and resource 'template draft' are specific, and the no-save/no-send distinction differentiates it from siblings like render_template.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises 'Use to test a template before create_template,' providing clear usage context. It does not mention when not to use or alternative tools, but the purpose is well-defined enough to infer usage boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the tool performs an immediate check with the provider ('right now') and returns fresh status, which is helpful. However, it does not mention any side effects, rate limits, authentication requirements, or whether the operation is read-only or could mutate state. This is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences that efficiently convey the purpose and usage recommendation. Every word earns its place, with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with only 2 parameters, no nested objects, and no output schema, the description is sufficiently complete. It explains what the tool does, when to use it, and what it returns. It could potentially mention that the check is synchronous and might take a moment, but overall it covers the essential 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 description coverage is 100%, so the description does not need to add extra meaning. The tool description does not elaborate on parameters beyond what the schema already provides (e.g., 'id' and 'sender' are well-documented in the schema). Thus, it meets the baseline without adding 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 clearly states the action (Re-check a domain's identity/DNS) and the result (return fresh status + per-record verification state). It specifies the resource (domain) and distinguishes from sibling tools like get_domain or add_domain.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly recommends using this tool 'right after publishing DNS records instead of waiting for the background poll,' providing clear context for when to use it. However, it does not explicitly mention alternative tools for checking current status without triggering a fresh verification.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Highlights the critical behavior that the plaintext secret is returned only once and must be stored immediately. Also notes scoping behavior. No annotations exist, so description carries full burden.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, concise and front-loaded with the most critical information (secret storage). Every sentence contributes meaningfully.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately covers the return behavior (secret once) and scoping. Lacks details on immediate activation or permission implications, but sufficient for a creation 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?
All 4 parameters have schema descriptions (100% coverage). The description adds value by clarifying senderId's role in scoping, but does not significantly enhance understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a new API key' with a specific verb and resource. It distinguishes from sibling tools like list_api_keys and revoke_api_key by focusing on creation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear guidance on optionally scoping the key to a product via senderId, and omitting for tenant-wide keys. However, it lacks explicit when-not-to-use or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the draft nature, one-time entry constraint, and free drafting. However, it does not mention permissions, rate limits, or error handling. The behavioral details are adequate but could be more comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, using a single paragraph that front-loads the main purpose. Every sentence provides relevant information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (6 params, nested objects, no output schema), the description explains the triggering and steps thoroughly. However, it lacks mention of the return value, which would be helpful for an agent to understand what to expect after creation.
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?
Schema coverage is 100%, but the description adds value by clarifying the structure of 'trigger' (one of three types) and 'steps' (1-20 items of specific types), and explains the XOR condition for email steps and 'approvalRequired' default. This goes beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool creates an automation DRAFT, not an active automation, and uses the specific verb 'Create' along with resource 'automation DRAFT'. It distinguishes from siblings like 'activate_automation' and 'update_automation' by emphasizing the draft state.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains that the automation runs nothing until activated, implying usage before activation. It also notes that drafting is free on every plan and that a contact enters each automation at most once, providing guidance on when to use this tool and its constraints. However, it does not explicitly state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral disclosure. It explains HMAC signing, event type list requirements, and that signingSecret is returned once. This adds useful behavioral context, though it omits details like idempotency 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two succinct sentences, each providing crucial information: purpose and key behavioral details. No redundant or extraneous content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description covers the creation behavior and the critical output element (signingSecret). It could mention the returned webhook object or error conditions, but the current completeness is good for a creation 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?
Schema coverage is 100%, providing descriptions for all parameters. The description adds value by clarifying eventTypes format (non-empty list, specific values) and the significance of signingSecret (returned once). For the URL and sender params, it supplements but mostly echoes the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a webhook endpoint that receives HMAC-signed event callbacks,' specifying the verb and resource. It distinguishes from sibling tools like list_webhooks, get_webhook, etc., by focusing on creation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides usage context by listing event types and noting that signingSecret is returned once, implying setup guidance. However, it does not specify when to use this vs. alternatives like update_webhook, or exclude cases like when to not create a webhook.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that deleting an automation also deletes its runs ('its runs cascade with it'). No annotations present, so description carries full burden; it adequately reveals this cascading behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, each serving a distinct purpose: main action with cascading effect, and usage condition. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Fully describes the core operation and constraints. No output schema exists, so no need to explain return values. Could mention error cases or permissions, but current content is sufficient given tool 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% (both id and sender described). Description does not add additional meaning beyond what schema provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
States the action 'Delete an automation by id' with a specific resource (automation). Differentiates from sibling tools like pause_automation by clarifying that runs cascade.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states the condition 'Only while draft or paused' and instructs to 'pause it first.' Provides clear context for when to use, but does not explicitly contrast with alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It mentions the 409 conflict response and that audit trail is preserved. It does not mention irreversibility, permission requirements, or side effects, but the provided details are adequate for a simple 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff. The first sentence states the action and required parameter, the second adds an important behavioral condition. Every word earns its place.
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 simple input schema (2 params, no nested objects) and no output schema, the description covers essential behavior. It could mention irreversibility or permission scopes, but overall it is sufficiently complete for a deletion tool in a CRUD 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%, and the description only adds 'by id' for the id parameter, which is already implied. No additional context for the sender parameter. The description adds marginal value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete) and resource (receive address/inbox). It distinguishes itself from sibling tools like list_inboxes and create_inbox by specifying deletion by ID, and adds a specific refusal condition (409 if inbox in use).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (when you want to delete an inbox) and when it will be refused (inbox has messages). It could explicitly state 'Use when you want to permanently remove an inbox' but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It explains upsert behavior, update-only semantics, and the special rule about resubscribing opted-out contacts. It also mentions the return object structure. This covers key behavioral traits, though some edge cases are not addressed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no superfluous words. It conveys all necessary information in a compact, front-loaded manner.
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 complexity of a batch upsert tool with behavioral nuances and no output schema, the description covers the main aspects: batching, update behavior, subscription rules, and return values. Missing details like error handling or rate limits are not critical for basic use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. The description adds value by explaining the 'sender' parameter's conditionality ('Required only for account-wide API keys; overrides default sender'), which goes beyond the schema description. The 'contacts' parameter is described as 'Rows to upsert (≤1000)' which matches the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs bulk import/upsert of contacts by email, distinguishing it from siblings like create_contact and update_contact which handle individual records. The verb 'import' and resource 'contacts' are specific, and the mention of batching adds clarity.
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 bulk operations with a 1000-row limit and batching advice, but does not explicitly state when to use alternatives (e.g., create_contact for single inserts) or when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
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 discloses key behavioral traits: new triggers stop matching, in-flight runs hold at their next step, and reactivation re-wakes them with unfinished waits honored. It does not mention idempotency, error handling for already paused automations, or required permissions, but covers the main effects well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently conveys the core action and its consequences. It is front-loaded with the purpose, then explains the effects. No unnecessary words. Structural clarity is high.
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 simple tool (2 parameters, no output schema), the description provides sufficient context about the tool's behavior. It explains what happens to triggers and runs. It could mention the return value or error conditions, but the tool's simplicity makes this acceptable. Slight gap in not describing the response 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 description coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the schema: the parameters 'id' and 'sender' are described in the schema with brief descriptions. The tool description does not elaborate on their semantics, so no incremental value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: pausing an active automation. It explains the effects on new triggers and in-flight runs, and explicitly distinguishes from related actions like reactivation. The verb 'pause' and resource 'automation' are specific, and the description differentiates it from siblings like 'resume_automation' and 'abort_automation'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly indicates when to use this tool (to temporarily pause an automation) and explains the behavior (new triggers stop, in-flight runs hold). It does not explicitly state when not to use it or mention alternatives like 'abort_automation' for permanent stoppage, but the sibling list provides context. A brief exclusion note would improve clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full burden. It discloses that the dispatch loop stops at its next batch and that already-queued messages still deliver, which is crucial behavioral detail beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. Front-loaded with the action and target, then adds precise behavioral constraints.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple mutation tool with no output schema, the description covers the key effect (pause with batch behavior) and resumption. Missing a mention of return value is minor given simplicity.
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 documented. The description does not add new meaning beyond the schema, which is acceptable per guidelines. 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 'pause' and target 'campaign', specifying it works on sending or scheduled campaigns. It distinguishes from siblings like resume_campaign and abort_campaign by mentioning resumption and batch behavior.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use (to pause a sending or scheduled campaign) and hints at when not to use (if you want to stop immediately, use abort_campaign is not mentioned but implied by sibling list). It could explicitly state to use abort_campaign for permanent stop.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses automatic threading headers, default From/To behavior, and override options. Missing details on whether the reply is sent immediately, any rate limits, or permissions required.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: first states purpose, second explains automatic behaviors. Every sentence adds value without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 9 parameters (1 required) and no output schema, the description covers the core behavior, default addressing, threading, and overrides. Missing details on return values, but acceptable given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds value by explaining defaults (From defaults to inbox address, To to original sender) and automatic behaviors (subject prefix 'Re:'). This context goes beyond the schema parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Reply to a received (or sent) message by id') and the resource (message by id). It distinguishes from sibling tools like send_email by specifying reply behavior, including automatic threading and default addressing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly guides usage by stating it is for replying to existing messages. However, it does not explicitly compare to alternatives like send_email or mention when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the primary effect (clears unsubscribedAt), but does not mention potential side effects or error cases. Still, for a simple mutation, this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that is front-loaded with the core action and parenthetical detail. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool is simple with 2 parameters and no output schema. Description covers purpose and parameter context adequately. Could mention behavior for already-resubscribed contacts, but not essential.
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?
Schema coverage is 100%, and description adds valuable detail for the 'sender' parameter: explains when it's needed and its purpose, which goes beyond the schema's description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action: opt a contact back in by clearing unsubscribedAt. The verb 'opt' and resource 'contact' are specific, and it directly contrasts with the sibling 'unsubscribe_contact'.
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?
Usage is implied (to reverse an unsubscribe), but no explicit guidance on when to use versus alternatives or conditions like idempotency. The context of sibling tools helps, but description lacks direct when-to-use instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description effectively discloses the immediate effect of cutting access and the refusal cases. This goes beyond just naming the action, adding important behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, each providing essential information. It is front-loaded with the action and concise, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and two parameters, the description effectively covers the tool's purpose, immediate effect, and restrictions. It could mention the return value or confirmation, but it is sufficient 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?
Schema description coverage is 100%, so the baseline is 3. The description does not add meaning beyond the schema; it only mentions 'by id' which is already covered. The 'sender' parameter is not addressed in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Revoke (delete) an API key by id', providing a specific verb and resource. It distinguishes itself from sibling tools like 'create_api_key' and 'list_api_keys' by indicating deletion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives context on when not to use it: refused for the key authenticating the request and internal service keys. However, it does not explicitly mention when to use this tool over alternatives like 'deactivate_key' if available.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description discloses key behavior: test_mode, no metrics/billing impact, and it exercises the full inbound path including webhooks.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single, well-structured sentence conveys essential information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 7 parameters, the description adequately covers purpose and key traits, though it could mention potential side effects like webhook triggers.
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 parameter details are already provided. The description does not add further meaning beyond the schema's descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it synthesizes a test inbound email, distinguishing it from real email sending tools. It specifies test_mode and the purpose of exercising the receive→thread→webhook path.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies testing by mentioning test_mode and exclusion from metrics/billing, but does not explicitly state when to use it versus alternatives like send_email.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It mentions the partial update nature, the state constraint (409 conflict), and which fields can be nulled. It does not cover authentication or rate limits, but provides meaningful behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that covers purpose, constraints, and null handling. It is front-loaded and efficient, though the null instruction could be separated for clarity. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 15 parameters, no output schema, and no annotations, the description leaves gaps. It explains null handling and state constraint, but does not cover return values, default behaviors for unmentioned fields, or permissions. Adequate but incomplete for complex 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?
Schema description coverage is low (13%). The description compensates by listing nullable fields and explaining that passing null clears them. It also clarifies the sender parameter's purpose. However, many parameters (e.g., name, fromEmail, approvalRequired) lack explanation. Still adds significant value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool updates a campaign by id with partial updates. It uses the verb 'Update' and the resource 'campaign', and distinguishes from sibling tools like create_campaign, delete_campaign, send_campaign, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the campaign must be in 'draft or pending_approval' state, and that a 409 error occurs if it is sending. It also instructs to pass an explicit null to clear nullable fields. While it does not list alternative tools for different states, the condition is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses that it's a partial update and lists updatable fields without rotating secret. However, it omits error scenarios, side effects, or authentication requirements, which could be important for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no wasted words. The key behaviors and constraints are front-loaded.
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 5 parameters, 1 required, no output schema, the description covers the core update behavior and constraints. It could mention idempotency or error responses, but is adequate for an update 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 schema covers 40% of parameters with descriptions. The description adds meaning for 'sender' (account-wide API keys override) and explains that url, enabled, eventTypes are updatable without secret rotation, compensating for the schema's gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'webhook by id', and specifies it's a partial update. It distinguishes from siblings like create_webhook and delete_webhook by noting specific updatable fields.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for partial updates ('Provide at least one field') and clarifies that the signing secret is not rotated. It doesn't explicitly state when not to use, but the context among siblings makes it clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It transparently states that the tool renders a template with merge data and returns the subject/html/text, and that it does not send. It does not mention authentication or side effects beyond merging, but is adequate for a non-destructive operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that wastes no words. It efficiently communicates the action, resource, and key behavioral detail (no send).
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?
No output schema exists, so the description must describe the return value. It mentions returning subject/html/text, but does not specify the format (e.g., JSON structure) or whether all fields are always present. This leaves some ambiguity for the 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?
Schema coverage is 100% and parameter descriptions are clear. The description adds value by explaining that the 'data' parameter is for merge variables, and implies the output includes the rendered fields. This adds context beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Render' and resource 'saved template', and clarifies what is returned (subject/html/text) and that it does not send. This clearly distinguishes it from sibling tools like send_email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states 'no send', indicating this tool is for previewing rather than sending. However, it does not explicitly compare with alternatives like preview_template or send_email, nor provide when-to-use or when-not-to-use guidance beyond the 'no send' flag.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the action is terminal and cannot be resumed, which is critical behavioral information. With no annotations, it carries the burden well, though it could mention return behavior or authorization needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three succinct sentences; front-loads the core action and consequence. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple action with full schema coverage and no output schema, the description covers the key behavioral context (terminal, human confirmation) adequately. Could optionally hint at return value but not necessary.
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 both parameters. The description adds no new parameter-level detail 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?
Description clearly states the action (abort campaign) and specifies the allowed states (scheduled/sending/paused/pending_approval → aborted), distinguishing it from siblings like pause_campaign and resume_campaign.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states the irreversible nature and advises human confirmation, guiding when to use (permanent stop) and when not (if resumption needed).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavioral traits: default approval-gating, email notification to account owner, approval required, immediate activation if false, handling of stranded runs, returned fields (status, pendingApproval), and prerequisites (paid plan, verified fromEmail domains) leading to error 403. No contradictions.
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 three sentences with no wasted words, but it could be slightly more concise by separating prerequisites. Still, it is well-structured and front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately mentions the return value (automation with status and pendingApproval) and error conditions. It covers all necessary context for safe 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?
Both parameters (id, sender) are described in the input schema with simple descriptions. The description does not add further meaning beyond the schema, which has 100% coverage. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Turn a draft or paused automation live.' It specifies the verb 'activate' and the resource 'automation', distinguishing it from sibling tools like 'pause_automation', 'create_automation', etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use this tool (to activate an automation) and provides critical context about the default approval-gated behavior and immediate activation when approvalRequired is false. It references campaign approval for analogy but does not explicitly state when not to use it or mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description discloses that resolution is always live and excludes unsubscribed/suppressed contacts. This adds valuable behavioral context beyond the schema.
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?
Three sentences, each adding value. Purpose is front-loaded, and the structure is clear and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description sufficiently covers inputs, behavior, and constraints. It provides enough information for a creation tool with nested objects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 75%, but the description adds detailed structure for the nested definition parameter, including fields, operators, and an example, which goes beyond the schema's brief description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with 'Create a saved audience segment' which is a specific verb and resource. It clearly distinguishes from siblings like list_segments, get_segment, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to omit definition to match every contact, and provides example usage. While it doesn't explicitly compare to alternatives, the context is clear enough for an agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the critical state restriction for deletion but omits permanence of deletion or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. The core action is first, followed by essential usage condition, making it front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 2-param tool without output schema, the description covers the key behavioral constraint and states. Missing return value info but still fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so description adds no extra parameter meaning beyond the schema's own descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Delete a campaign by id' and distinguishes it from sibling campaign tools by specifying allowed states, differentiating from pause, abort, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit allowed states ('draft/pending_approval/completed/aborted') and instructs to pause or abort a mid-flight campaign first, offering clear when-not-to-use and alternative actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the burden. It reveals the important fallback behavior but does not mention irreversibility, required permissions, or potential errors. Still, the key side-effect is 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?
Two sentences, each serving a distinct purpose: action statement and warning. No wasted words; information density is high.
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?
Lacks output schema and no annotations. The description covers the action, side-effect, and caution. Missing details on return value or error conditions, but adequately complete for a simple delete 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% (both parameters have schema descriptions). The description adds no extra parameter meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description begins with 'Delete a segment by id', specifying a clear verb and resource. It distinguishes from sibling tools like delete_campaign or delete_contact by including the unique side-effect about campaigns falling back.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states the consequence of deletion on campaigns and advises to check before deleting, providing clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses ordering (newest first), the presence of counters, and the filter capability. It does not explicitly state that the tool is read-only or non-destructive, but the verb 'list' implies a read operation. It also mentions pagination parameters (limit, cursor) implicitly through the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, each earning its place. The first sentence states the core purpose and ordering; the second gives a concrete usage example. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema, the description mentions 'status + counters' but does not detail the counters or the full response shape. It also doesn't explain pagination behavior beyond schema parameters. However, for a simple list tool with high schema coverage, it is fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining the status filter use case ('pending_approval campaigns waiting on a human') and reinforces the limit default/max. The cursory explanation for sender is not in description but in schema. Overall, it provides meaningful context beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List campaigns' with the verb 'list' and resource 'campaigns', and distinguishes campaigns as 'many-recipient sends' from other tools like list_templates or send_email. It also mentions the output includes status and counters, and provides a concrete example (pending_approval).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a clear use case: filter by status to find pending_approval campaigns. However, it does not explicitly mention when to avoid this tool or compare it to sibling tools like get_campaign (single campaign) or search functionality. The context is clear but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behaviors: from must be on verified domain, sender required for account-wide API keys, idempotency key 24h dedup. No annotations, so description carries burden; could mention return value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, no wasted words. Easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 15-parameter tool with no output schema, description covers main sending modes and constraints. Could elaborate on parameter interactions, but sufficient for typical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (baseline 3). Description adds meaning: address format ('Name <email>'), templateId as id/slug, subject optional with templateId.
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 'Send a transactional email' with a specific verb and resource, distinguishing it from sibling tools like send_batch and reply_email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides guidance on using inline html/text versus template rendering, and address format. Lacks explicit exclusions or when-not-to-use alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses fire-and-forget automation triggering, durable storage, and the side effect of creating a new contact for unknown emails. Missing details on error handling for missing or conflicting parameters, but still informative.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, each sentence adds essential information: purpose, identification, side effects, and return value. No unnecessary words or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters and no output schema, the description covers input constraints, behavior (fire-and-forget, durable), and return shape (202 accepted). It lacks error scenarios but is adequate for a fire-and-forget event 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?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining the XOR constraint for email/contactId, the conditional requirement for sender, and the 8KB limit for payload, which are not in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it records a custom event about a contact, provides examples like 'order_placed', and specifies identification by email or contactId. It distinguishes from sibling tools by focusing on event recording.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the XOR constraint for email or contactId and mentions that an unknown email creates a new contact. It does not provide explicit when-not-to-use guidance, but the usage context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses key behaviors: partial update, state requirement, steps replacement, and topicId null usage. Could add more on field merge semantics but is substantial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with main action and crucial constraint. No redundant information. Every sentence earns its place.
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?
Covers essential behavioral context for a complex tool (partial update with state machine, 7 params, nested objects). Lacks return value explanation (no output schema) but provides sufficient guidance for correct agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (43%). Description adds value for steps ('replaces the program wholesale') and topicId ('null to clear'), but other parameters (sender, approvalRequired, trigger, name) lack elaboration. Partially compensates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and resource 'automation', specifying partial update ('by id (partial)'). It distinguishes from sibling tools like create_automation, delete_automation, and activate_automation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit condition: 'only while draft or paused (pause an active one first)'. This directly guides when to use the tool and implies the need to use pause_automation first, which is a sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Clearly states it does not save or send anything, and returns count and sample. No annotations provided, but description covers non-destructive nature and output. Could elaborate on auth needs or rate limits, but sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no unnecessary words. Front-loaded with key behavior (resolve without save/send), then details. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
In absence of output schema, description explains return values (count and sample ≤10). Covers both input modes (segmentId or definition) and use case. Complete for a preview 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?
Schema coverage is 100%, so baseline is 3. Description adds structure details for 'definition' (inline {match, conditions[]}) beyond schema's generic type:object, improving clarity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool resolves an audience without saving or sending, distinguishes from sibling segment tools like create_segment, update_segment, delete_segment, list_segments, get_segment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this to sanity-check a filter before attaching it to a campaign', implying when to use. Does not explicitly mention when not to use or alternatives, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: 'Re-runs the send gates, transitions it to scheduled, and starts dispatch.' This explains the side effects clearly. There is no contradiction with 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences: the first states the core purpose and alternative, the second explains effects and usage condition. No unnecessary words, front-loaded with essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema and no annotations, the description covers all necessary aspects: what the tool does, its side effects, and when to use it. It is fully adequate for an agent to select and 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%, providing good parameter documentation. The tool description does not add any additional semantic value beyond the schema for the 'id' and 'sender' parameters. Thus, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'Approve a pending_approval campaign via the API'. It distinguishes this tool from siblings by specifying it's for approval, while other campaign tools like list_campaigns or send_campaign serve different purposes. The verb 'approve' and resource 'campaign' are explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to call: 'Only call this when the human has EXPLICITLY confirmed they want the blast to go out.' It also provides context by mentioning it's an alternative to replying to an approval email, aiding decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavior: it creates a draft, nothing sends, approvalRequired parks for human approval, audience gating logic, and that drafting is free. No hidden side effects are omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient paragraph with no wasted words. It front-loads the critical action and provides essential details in a logical order. Every sentence contributes meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description does not need to explain return values. It covers input parameters comprehensively and organizes them logically. It could mention that the campaign ID is returned, but the description is already very complete for agent 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?
Schema coverage is 100%, so baseline is 3. The description adds significant value by explaining the overall logic (audience, content options, approval) and constraints like 'never both' for template vs inline content, going beyond individual parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it creates a campaign DRAFT and explicitly distinguishes from send_campaign. It specifies the verb 'Create', the resource 'campaign', and the state 'DRAFT'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool (to create a draft), contrasts with send_campaign, explains audience selection via segmentId/topicId, content options (templateId vs inline), and the approvalRequired flag with default behavior.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses that the campaign does not send immediately, parks in pending_approval, re-sends approval email on re-call, and fails with 403 if requirements are unmet. No contradictions.
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 detailed but somewhat lengthy. However, all information is essential and well-organized, front-loading the key behavior. Minor redundancy could be trimmed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given complexity (async approval, errors, requirements) and no output schema, the description is highly complete. It explains return value (campaign resource with status) and error conditions.
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?
Schema coverage is 100%, but description adds meaning: explains 'sender' is for account-wide keys and overrides default. The 'id' parameter is clarified as campaign id, providing context beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it 'Request the campaign blast' and distinguishes itself from sibling tools like dry_run_campaign by detailing the pending approval flow. It's specific about the 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 Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs 'ALWAYS run dry_run_campaign first' and explains when it requires a paid plan, verified domain, and the behavior of re-calling. Provides clear context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that 'Nothing is enqueued' (non-destructive), explains what is returned (count, exclusions, samples), and mentions safety rails. No annotations provided, so description fully covers behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with purpose and key behaviors, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description sufficiently explains return values (count, exclusions, rendered samples) and usage context, making it complete for a preview 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?
Schema coverage is 100% with parameter descriptions. Description adds context for 'sender' (product/sender externalId) and clarifies its use for account-wide API keys, slightly exceeding baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Explicitly states 'Preview exactly what a campaign WOULD send' with specific outputs (net recipient count, excluded contacts, samples). Clearly distinguishes from send_campaign, a sibling tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Directly instructs to 'ALWAYS call this before send_campaign' and to 'sanity-check the count and rendering with the user,' providing clear when-to-use guidance.
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:

[![drin-mcp MCP server](https://glama.ai/mcp/servers/ATOM00blue/drin-mcp/badges/card.svg)](https://glama.ai/mcp/servers/ATOM00blue/drin-mcp)

Score Badge

Copy to your README.md:

[![drin-mcp MCP server](https://glama.ai/mcp/servers/ATOM00blue/drin-mcp/badges/score.svg)](https://glama.ai/mcp/servers/ATOM00blue/drin-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/ATOM00blue/drin-mcp'

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