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

The annotations only indicate readOnlyHint=false, and the description adds meaningful behavior: 'WRITES: this call changes stored state and is not safe to repeat blindly' and 'Revocation is a dated boundary, never retroactive.' This goes beyond the minimal annotation by warning about non-idempotence and temporal scope.

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?

The description is concise and front-loaded with the core action. Each sentence adds distinct value: the action, the signature mode distinction, the temporal boundary, and the write/non-idempotence warning. There is no wasted text.

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?

The description covers the key behavioral context: write side effects, non-idempotence, and the meaning of signed vs. unsigned revocation. However, it omits any explanation of the required 'secret' parameter and does not mention what happens on repeat calls or after revocation, leaving a small but notable gap.

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?

The schema describes thumbprint and signature, and the description adds useful semantics for the signature parameter by explaining that including it records the strong form while omitting it records bearer-credential revocation. However, the 'secret' parameter is left entirely unexplained in both the schema and the description, so parameter semantics are only partially covered.

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 states a specific action: 'Revoke one of your bound keys.' This clearly identifies the tool's purpose and resource. However, it does not explicitly distinguish this from sibling tools like decline_key or rotate, so it lacks sibling differentiation for a top score.

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 provides operational warnings and explains the two revocation forms (signed vs. unsigned), but it does not state when to use this tool over alternatives or when not to use it. There is no guidance about tool selection among the many sibling tools.

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