Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are minimal: readOnlyHint=false (write operation), destructiveHint=false, idempotentHint=false. The description adds the fact that it writes to the same log as the site's widget and requires the user's email for follow-up. However, it does not disclose the idempotency behavior (despite an idempotency_key parameter) or any rate limits, though these are not explicitly contradicted. The description adds some context but misses important operational details for a write tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, with the core purpose front-loaded and the email requirement stated immediately. Every word adds value—no filler. The structure is ideal for an agent scanning quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 10 parameters (including enums, idempotency_key, sandbox), the description is quite thin. While the schema fully documents each parameter, the description does not explain when to use idempotency_key (e.g., for retries) or how sandbox relates to testing, which would be helpful for correct usage. There is no output schema, so the description doesn't need to cover return values. The description is adequate but lacks guidance on edge cases that a complex tool would benefit from.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%—every parameter has a description. The description itself adds little beyond what the schema already provides; it merely highlights the email requirement, which is already documented. There is no explanation of the idempotency_key's role or how sandbox works, but the schema covers these fields adequately. This meets the baseline of 3 for tools with full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: 'Files feedback (bug, idea, friction, praise, other) with the COTAL team on behalf of the user.' It uses a specific verb and resource, and the list of types matches the enum in the schema. It distinguishes from sibling tools (e.g., cotal_request_call, cotal_subscribe_newsletter) by focusing on feedback rather than other actions. The additional detail about the site's feedback widget further anchors its purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it (when the user has feedback to submit) but does not explicitly contrast it with alternatives like requesting a call or subscribing. It does mention the email requirement, which is a key prerequisite. There is no explicit 'use this instead of X' guidance, but the purpose is specific enough that an agent can reasonably infer the correct context. A clear exclusion list would elevate this to a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.