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

With no annotations, the description carries the full behavioral burden; it does disclose the data source, the cost ($0.25 USDC), and the field set an agent can expect. It does not say what happens on no-match or invalid SIREN, whether results are cached, or how the response is shaped, and it is silent on the fact that five optional params allow ambiguous/conflicting calls.

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 capability, search keys, example, price and alternatives are all front-loaded in three dense clauses with no filler. The field enumeration is list-like but each term earns its place as a coverage signal; only the terse related-services shorthand (/kyb $2.50 (pass siren=)) is slightly compressed to the point of ambiguity.

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 and no annotations, the description does useful work by listing returned fields and the price. However, for a 5-param tool with zero schema coverage and no required fields, an agent still cannot tell how to choose between q and name, what limit does, or what a failed lookup returns.

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 0% and none of the five params have descriptions, so the description must compensate; it partly does by naming siren, siret and name as valid search keys and giving a siren example. It adds nothing about q (which appears redundant with name), limit's string-or-number type, or defaults/constraints, leaving two of five params entirely unexplained.

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 ('French company lookup'), names the upstream registry (API Recherche d'entreprises / INSEE/RNE), and enumerates the returned fields (name, SIREN, status, NAF, siège, dirigeants, finances, red flags). The jurisdiction prefix plus the 'Related' routing line makes it trivially distinguishable from uk_company, us_sec, eu_vat and the other registry siblings.

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?

Gives concrete invocation shapes ('Search by siren, siret, or name') and an inline example {siren:"443061841"}, plus explicit routing to kyb (pass siren=), eu_vat, sanctions_screen and registry_batch with prices. It stops short of stating exclusions (e.g. when to prefer company_full or registry_batch over this tool), so it is strong context rather than a complete decision rule.

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