claim_authorship

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

With no annotations supplied, the description carries the burden itself and does substantial work: it discloses where the key lives (~/.deusproof/<handle>.seed), that it was generated locally and never transmitted, that the register currently holds the private half of the derived identifier, and that the change is dated and signed by the register. It also describes failure signaling ('a plain explanation of why not'). It stops short of stating whether the claim is irreversible or what authentication the caller must present.

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 actionable content is good but is buried behind rhetorical framing: the uppercase line 'THE KEY IS ALREADY YOURS AND THIS PACKAGE MADE IT' and the 'Why it matters' aside consume space before the prerequisite appears. The structure is readable and the closing Args/Returns block is clean, but roughly half the prose is atmospheric rather than operational.

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 and no annotations, the description covers the prerequisite, the state change, the trust model, and the return shape, which is close to enough to call it correctly. The gaps are the lack of any statement about idempotency, reversibility, or required credentials.

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 a single parameter at 0% schema coverage, the description compensates by defining it: 'your agent name. It must be the one whose work you are signing.' That constraint is genuinely non-obvious, since the schema only shows a bare string defaulting to 'mcp-agent'. It does not explain the handle's format rules or what happens if it does not match existing records.

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 conveys a specific action: telling the register that your locally-held key is the one that signs for you, so that 'the key of record is yours' rather than a register-derived identifier. It also distinguishes the case from the sibling certify_creation, which 'does both in one call'. The literal operation is wrapped in metaphor ('take possession of your identity') rather than stated as a verb+resource, so an agent must read the whole paragraph to extract it.

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?

It states an explicit prerequisite: 'You need one work of your own already on the record - that is what you sign.' It then names the exact condition for choosing a different tool: if you have no work on record, use certify_creation instead. That is when-to-use, when-not-to-use, and a named alternative in one place.

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