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

The description goes beyond the readOnlyHint annotation by explicitly stating 'READ-ONLY: this call changes nothing and can be repeated safely' and 'Reads nothing about anyone else and creates nothing; it is a string builder.' It also discloses the replay-prevention property and the requirement to send issued_at back with the signature. This adds meaningful behavioral context beyond the annotation.

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 dense but well-structured, front-loading the core purpose and then explaining key properties. It is somewhat long but every sentence adds value: the replay-prevention property, the issued_at requirement, and the read-only guarantee are all important. The READ-ONLY note is repeated, which is slightly redundant with the annotation, but it is useful for emphasis.

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 5 parameters, the description covers the critical usage details: what the preimage is, how to sign it, the replay-prevention property, and the issued_at requirement. It does not explain the secret parameter or the exact format of the returned bytes, but the description's emphasis on 'sign what you fetched' mitigates the need for format details. The sibling context includes signing_bytes, which may be the alternative for other signing needs, but the description does not explicitly route to it.

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 40%, so the description must compensate. It explains the role of issued_at ('part of the signed bytes and must be sent with the signature') and clarifies that verdict is 'pass' or 'fail'. It also explains the overall purpose of the parameters (building preimage bytes). However, it does not explain listing_id and submission_id beyond their names, and secret is not mentioned in the description.

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 clearly states the tool's purpose: it builds the exact bytes a verifier signs to record a PASS or FAIL on one submission. It distinguishes itself from siblings by emphasizing it is a string builder that reads nothing and creates nothing, and by explaining the one-preimage-per-outcome property.

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 gives clear context for when to use this tool: when you need to sign a verdict for a submission, and it explicitly says to sign what you fetched rather than what you assembled. It also warns that issued_at must be sent with the signature. However, it does not explicitly name alternative tools or state when not to use it, though the sibling list includes signing_bytes and attestation tools that could be alternatives.

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