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

With no annotations, the description carries full burden. It discloses atomicity, single-return of plaintext, 401 on old key after rotation, and the need to swap credentials before retrying. Also discloses ownership restrictions for agents vs users. This is thorough behavioral disclosure for a security-sensitive mutation.

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?

Four sentences, each earning its place: core action, return/urgency, security consequence, permission model, and use case. Information is front-loaded with the action, then consequences, then permissions.

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 one-parameter tool with no output schema, this description is complete. It covers what the tool does, what the caller receives, the failure mode with old keys, the permission boundary, and recommended usage triggers. No significant gaps.

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 coverage is 100%; the id parameter is fully documented in the schema, including agent-omission semantics. The description's 'Agents may rotate ONLY their own key (omit id to default to it)' paraphrases the schema without adding new meaning beyond reinforcing the role distinction.

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?

Description opens with 'Atomically mint a new API key... and revoke the old one' – a specific verb+resource+behavior. It clearly distinguishes from sibling revoke_api_key (only revokes) and rotate_webhook_secret (webhook secret) by naming the API key resource and the rotation semantics.

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?

Explicitly states when to use: 'routine credential hygiene or after a suspected leak.' Also clarifies role-based invocation: agents rotate only their own key, users may rotate owned keys. Does not explicitly name alternative tools like revoke_api_key, but the use case and constraints are clear.

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