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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lower, and the description still adds genuine value by disclosing the shape of the result: findings bucketed into code-fixable vs. spec-authoring, with per-generator remediation. What it omits is behavior on ambiguity — whether it reports a confidence, or what happens when no generator fingerprint is recognized.

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?

A single dense sentence that front-loads the operation and then the diagnostic output. Every clause earns its place except the 'PRO —' marketing prefix, which conveys no actionable information to an agent and slightly delays the verb.

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?

With no output schema, the description must convey the return shape, and it does: generator identification plus two categorized finding buckets plus per-generator remediation. Combined with complete parameter documentation and read-only annotations, this is nearly sufficient; the only gap is edge-case behavior when a fingerprint cannot be determined.

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 100%, so both `document` (accepted formats, string or object) and even the unusual `context` parameter are fully documented in the schema. The description adds nothing about either parameter, so the baseline 3 applies — the schema carries this dimension entirely.

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 — 'identify which OpenAPI generator produced the spec' — and adds the output shape (findings split between code-annotation fixes and spec-authoring fixes). That is far more specific than the name alone and clearly distinct from generic validators or linters in the sibling list. It does not explicitly name the adjacent sibling (detect_format for spec-type detection), keeping it just short of a 5.

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?

'For a code-first API' is a real qualifying condition that tells the agent when this applies, which is more than nothing. But there is no when-not guidance (e.g., design-first specs), no named alternative, and no statement of prerequisites such as needing the source spec rather than a hosted URL. Usage is only implied.

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