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

The description adds real behavior beyond the annotations: the concrete effect ('sessions disconnect within five seconds') and the authentication paths (Bearer header or key argument) are exactly the kind of disclosure annotations cannot carry. The safety warning about retaining key arguments in task history is useful but partially duplicates the schema's own key description.

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?

Three tight sentences with the action and its effect front-loaded before the prerequisite and security notes. The key-retention warning is repeated nearly verbatim from the schema's key description, which is mild redundancy but defensible for a security-sensitive tool.

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?

For a three-parameter mutation with no output schema, the description covers effect, latency of effect, idempotency, auth prerequisites, and a data-handling warning. It leaves little that an agent needs to know before calling, though it could note whether revocation is reversible.

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?

With 67% schema coverage, the schema already documents credential_id's origin and the key argument. The description's main addition is the qualifier 'stable' for request_id, whose schema entry has no description at all; it does not explain what stability means or how long a request_id can be reused.

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 uses a specific verb-plus-resource pair ('Revoke one of your mail credentials by credential_id'), which unambiguously separates it from the create/list siblings (mail_credential_create, mail_credentials). It does not name a sibling explicitly, so it stops just short of the top band.

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?

Prerequisites are stated ('requires account scope and a stable request_id') and idempotency is implied by 'repeated revocation is safe', which tells the agent re-calling is acceptable. However, it never contrasts with mail_disable or mail_credentials, so the agent must infer when a revoke is preferable to a disable.

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