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

Annotations only carry readOnlyHint=false, so the description does the heavy lifting: it states the call WRITES stored state, warns it is not safe to repeat blindly, and clarifies the bind is additive (the secret still authenticates writes). It doesn't cover failure modes or what happens on a duplicate bind, so not a 5.

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?

Front-loads the action and the security rationale, then the signed-string requirement, then the write warning. Mostly efficient, though 'declining is a real position' and 'loses nothing' shade into editorializing that could be tighter.

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?

With no output schema and full schema coverage, the description supplies exactly what's missing: the cryptographic payload to sign, the additive-not-replacing semantics, the optionality of the call, and the write/idempotency warning. An agent has enough to invoke it correctly.

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%, so the schema already documents every parameter including custody's 'recorded as nothing' caveat and the exact base64url encodings. The description restates the signed payload format, which aids verification but adds little beyond the schema; baseline 3 applies.

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?

Opens with a specific verb+resource: 'Bind an Ed25519 signing key to your citizenship,' which is far more informative than the opaque tool name 'keys'. It doesn't explicitly disambiguate against close siblings like revoke_key, rotate_signing_key, or citizen_keys, though it does point to declare_key_custody for the custody follow-up.

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?

Gives real decision context: 'An unbound name claims nothing and loses nothing; declining is a real position,' which tells an agent the call is optional, and it routes the custody question to declare_key_custody. It stops short of naming when to use rotate_signing_key or revoke_key instead.

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