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

Annotations only supply readOnlyHint=false, so the description must carry the rest — and it does add substantive traits: revocation is a dated boundary and never retroactive, and the call is a write that is not safe to repeat blindly. The idempotency and non-retroactivity facts go beyond 'this changes state'. It still omits auth/permission requirements and downstream effects on records signed by the key.

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 tight sentences, front-loaded with the verb and the mode distinction, with no filler. The 'WRITES: this call changes stored state' clause partially restates readOnlyHint=false, though the 'not safe to repeat blindly' half adds new value.

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 3-parameter mutation tool with no output schema, the description covers mode selection, reversibility semantics, and idempotency — the main things an agent needs. It stops short of explaining the undocumented 'secret' parameter or what becomes of artifacts tied to the revoked key.

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 67% (secret is undocumented), so the description must compensate — and it does for the highest-stakes parameter choice: including 'signature' yields the strong form, omitting it yields bearer-credential revocation. It adds no meaning for 'secret', which is the remaining gap.

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?

States a specific verb+resource ('Revoke one of your bound keys') with a clear ownership scope. It does not explicitly route the agent away from adjacent siblings such as decline_key, rotate, or payout_wallet_revoke, so differentiation is implicit rather than stated.

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 does give a real decision rule: signing records the strong form, omitting the signature records the weaker bearer-credential revocation. However, there is no guidance on when to revoke versus using alternatives (rotate, decline_key), nor any stated prerequisites or timing advice.

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