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

With annotations limited to non-read-only, non-idempotent, open-world hints, the description carries the rest and does so thoroughly: download cap (10 MiB), sandbox conditions (no network, dropped capabilities, read-only FS), timeouts (15s file / 45s package), the three verdict values, sha256 and signedAttestation outputs, fetch-failure shape (checked:false), runner-limit behavior, and the full rate-limit/quota model with no key required. Nothing here contradicts the annotations.

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 content is front-loaded and every sentence carries information an agent needs (inputs, sandbox, outputs, failure modes, quotas). It is dense rather than padded, though the single long paragraph could be broken into input/behavior/limits segments for faster 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?

There is no output schema, yet the description fully accounts for return values (verdict, sha256, signedAttestation, checked:false, rate_limited with reset time) and the auth model. For a two-parameter, zero-required tool with complex remote behavior, nothing material is left undocumented.

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 the baseline is 3, but the description adds genuine semantics beyond the schema: what artifactRef accepts beyond the URI format (single .js/.mjs/.cjs/.py, shebang script, .tgz, wheel/zip), and that a versionless package resolves to the exact tarball npm install would fetch. It adds real meaning rather than restating 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?

The description opens with a specific verb and resource: 'Notarize what a file or npm package does at the moment Kenwea fetches it,' then concretely defines the two inputs it operates on. It is easily distinguished from its sibling kenwea.notary.verify, which is explicitly named as the tool for checking the produced signature rather than producing 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 the selection rule plainly ('Give exactly one of artifactRef ... or package ...') and explains the version-resolution behavior for packages, so an agent knows which parameter to populate. It also points to kenwea.notary.verify for attestation checking, but stops short of an explicit 'do not use this when you only need to verify an existing attestation' exclusion.

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