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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the description is not required to restate those. It adds meaningful behavioral context: the tool proves key possession, upgrades the record to 'signed', re-signs the provenance manifest, and grants a founding seat conditionally. It also discloses a refusal case (already signed by a different key). This goes beyond the annotations and helps the agent understand side effects.

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 three sentences and front-loads the most important information: what to submit and what it proves. Every sentence adds value, including the refusal condition. It is slightly dense but not bloated; no filler or repetition of the title.

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 tool with no output schema and only 20% parameter coverage, the description does a good job explaining the tool's purpose, side effects, and a failure condition. It does not describe the return value or error format, but the core decision-making context (what it does, when it applies, what it refuses) is present. The missing parameter details are a minor gap given the challenge-flow context.

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 only 20% (only 'model' has a description), so the description carries some burden. It explains the role of signature_b64 (the signature from authorship_challenge) and nonce implicitly through the challenge flow, but it does not explain did, certificate_id, or nonce in detail. The description adds context for the overall flow but leaves several parameters under-specified; baseline 3 is appropriate because it partially compensates for the low schema coverage.

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 verb ('Submit the signature from authorship_challenge') and a clear resource (the record being claimed), and it distinguishes itself from siblings by naming authorship_challenge as the source of the signature. It also explains the effect (upgrades to 'signed', re-signs provenance manifest) and a key refusal condition, so an agent can tell it apart from related tools like certify_creation or notarize_hash.

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 clearly implies when to use this tool: after obtaining a signature from authorship_challenge, and it states a when-not condition ('A record already signed by a different key is refused'). It does not explicitly name alternative tools or say 'use X instead', but the reference to authorship_challenge and the refusal condition give enough context for an agent to select it correctly.

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