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

With no annotations, the description carries the full behavioral burden and does it well: it discloses algorithm dispatch limits (-7/-35/-36 and -8), the success-response quirk that verified=false is a successful response with a reason, and the key-source fallback behavior. It could additionally clarify behavior for unsupported algorithms or missing certificate fields, but the disclosed traits are genuinely informative.

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 organized into labeled sections (algorithm, parameters, output, notes) and front-loads the tool's purpose before diving into details. Some parameter text repeats the schema, but every section contributes meaningful information and the structure aids scanning.

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?

Given no output schema, the description compensates by listing the return fields and explaining the unusual verified=false success semantics. It covers key behavior, key-source resolution, input size limits, and the output payload. Minor gaps remain around detached-payload handling and specific error cases, but overall the agent has enough context to call the tool 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 coverage is 100%, so each parameter is already documented in the input schema. The description adds some useful nuance, such as the external AAD needing to match the signing-time value and the public-key fallback to the certificate, but these largely duplicate or only lightly extend the schema descriptions. It also omits detached_payload_in_hex from its parameter list, though the schema covers it.

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 opens with a specific verb-resource pair: '验证 COSE_Sign1 签名' (verify COSE_Sign1 signature) and anchors it to RFC 9052 §4.4 Sig_structure reconstruction. It also enumerates supported algorithms, which clearly distinguishes this tool from cose_sign1_parse and cose_sign1_sign.

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 operational context: when to provide a PEM key versus leaving it empty to extract from the payload certificate, and that external_aad_in_hex must match the value used at signing time. It does not explicitly state when to prefer this over siblings, but the verification purpose and parameter conditions make the intended usage clear.

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