verify_manifest

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

With no annotations, the description carries the burden well: it discloses the internal mechanism (recompute manifest hash, then check signature) and a genuine coverage limit for v3 signatures. It does not say what failure looks like (exception vs. falsy result) or whether partial trust is signaled, which keeps it below 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?

Four short sentences, each doing distinct work: purpose, mechanism, usage trigger, and a scope caveat. The verb and resource are front-loaded with zero filler.

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 nested-object input with no output schema, the description should indicate the return shape (boolean vs. a result object with failure reasons). It covers inputs, mechanism, and scope but leaves the outcome contract unstated.

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 both parameters are already documented as an object and a PEM SPKI Ed25519 key; baseline is 3. The description reinforces that the key must be Ed25519 and that the manifest is a signed envelope, but adds no format or constraint detail beyond the schema.

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?

Names a specific verb and resource ('Verify a signed receipt bundle manifest'), pins the exact artifact (MANIFEST.signed.json) and the algorithm (Ed25519). It is unmistakably different from the build_* sibling tools, which all generate reports rather than validate inputs.

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?

'Use before building a report from a receipt set you did not produce yourself' gives a concrete triggering condition and ties it to the downstream build_* workflow. It also states a negative scope ('Does not check the ML-DSA-65 half'), though it names no explicit alternative tool for that case.

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