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

Beyond annotations, the description adds useful behavioral context: coverage depends on public sources, and there is a per-call price of 0.020 USD via x402. The safety disclaimer about legal/credit/fraud-free use is also valuable. The 'Searches' language is roughly consistent with a non-destructive operation and does not directly contradict the readOnlyHint=false annotation, though it does not explain why that hint is false.

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 description is compact and front-loaded with the core search purpose. It loses structure points because the 'Use when' section is a verbatim repeat of the opening sentence, which wastes one of its few sentences.

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 14-parameter tool with zero schema descriptions and no enums, the description is not complete enough to support correct invocation without additional lookups. The output schema covers return values and the price/limitations notes are helpful, but parameter semantics and code-list sources are missing, and no pointer to sibling tools like list_categories is given.

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 0% across 14 parameters, so the description must compensate but only does so at a high level. It maps broad filter categories (activity, geography, size, certifications) to some parameters, but leaves cryptic parameters like bio, rge, qualiopi, legal_form_code, and employee_band_code without value semantics or code-list guidance, and query/page/limit are not mentioned at all.

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: 'Searches active French companies using structured public B2B filters such as activity, geography, size and supported certifications.' It makes the tool's scope and filtering nature clear, but it does not explicitly distinguish this from close siblings like company_fr_search or company_fr_profile.

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 provides an explicit avoidance boundary ('Do not use this endpoint as a legal, regulated credit or guaranteed fraud-free decision') and a limitations note, which helps set expectations. However, the 'Use when' line simply repeats the first sentence, and it never names alternatives or says when one of the other company_fr_* tools would be better.

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