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

Beyond the readOnly/idempotent/closed-world annotations, it discloses meaningful behavior: counts are never fabricated, unknown or unreviewed products return found:false, and low/high counts carry no quality implication. It does not cover edge cases such as products with partial evidence or response size.

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?

Front-loaded with identity and scope, then a compact enumeration of returned fields and the fallback behavior. The anti-misinterpretation caveat is worth its space, though the single dense paragraph could be split for scanability.

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 carries the full burden and does so: it enumerates every returned field (outlets, labs, metrics, mentioned, reading) and the found:false failure shape. An agent has everything needed to call it and interpret the response.

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% and both parameters already carry example values. The description only restates that lookup is by category + slug, adding no format, casing, or resolution rules beyond the schema — baseline 3 applies.

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?

States a specific verb+resource: the independent-testing provenance for ONE product identified by category + slug, and clarifies it is a COUNT of evidence, not a quality score. Scope is unambiguous, but it never names the sibling it is differentiated from (e.g. list_coverage, get_benchmark), so an agent must infer the boundary.

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 gives strong interpretive guidance — low count does not mean a bad product, high count does not mean better — but that is about reading results, not about when to select this tool over siblings. No explicit when-to-use/when-not-to-use or alternative routing is provided.

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