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

Annotations declare readOnlyHint=true and openWorldHint=false, so the safety profile is already given, and the description credits the report contents (resolved, newly fires, breaking changes), which is real added value. However, 'apply it' reads like a mutation and is in tension with readOnlyHint=true — an agent cannot tell whether the overlay is applied to the passed-in document only or persisted. That ambiguity is exactly what a description should resolve when annotations say 'no side effects'.

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?

Two tightly packed sentences with the outcome front-loaded and no filler. The 'PRO —' prefix is low-cost framing, though the trailing 'Review the overlay before applying it' introduces a workflow step the schema cannot satisfy.

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 is what tells the agent what comes back, and it does so specifically: what was resolved, what newly fires, and any breaking change. The gaps are the undocumented `rules` selector and the absence of any way to actually preview the overlay before it is applied.

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 fully documented in the schema, and the baseline of 3 applies. The description does not add meaning to `document` or `context`, and it references a `rules` input that does not appear in the schema at all, which is mildly confusing rather than helpful.

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 names a concrete verb chain and resource: propose an OpenAPI Overlay that fixes lint errors, apply it, re-lint, and report. An agent immediately knows this is a generate-and-verify remediation tool. It does not, however, distinguish itself from the sibling apply_overlay or test_ruleset, so the boundary only becomes clear from the schema.

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?

Usage is implied rather than stated: you come here when lint errors need fixing, and the phrase 'or the `rules` you name' hints at a targeted variant. There is no explicit when-to-use versus apply_overlay (which takes a pre-built overlay) and no when-not guidance. 'Review the overlay before applying it' is a workflow hint, but there is no dry-run parameter to support it.

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