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

Annotations carry little signal (all hints false), so the description does the heavy lifting. It discloses the payment side effect (records not modified but x402 payment consumed, challenge is free, repeats may require new payment), cursor binding to search context, and that non-diffusible restricted data is excluded. This adds meaningful behavior beyond the annotations. No contradiction with annotations since the financial side effect justifies readOnlyHint=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 long but justified: it is a paid tool requiring pricing, network, and payment-behavior disclosures. It is well-sectioned (Use when / Avoid when / Limitations / Price / Paid-call behavior / Accepted networks) and front-loads the core function before the pricing details. Each section earns its place.

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?

An output schema exists, so return values are covered by structured data. The description covers purpose, usage routing, limitations, pagination semantics, and the full payment model. For a paginated, paid, read-oriented tool this is near-complete; only worked examples or error-case handling are absent, which is minor.

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%, with all three parameters (identifier, limit, cursor) documented in the schema. The description adds marginal value by reinforcing that the cursor is opaque and bound to its search context and should only be reused for the same query. Per baseline rules, with full schema coverage a 3 is appropriate.

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 (returns), resource (public establishments), data source (official Sirene), and content (status, activity, address). It clearly distinguishes itself from company_fr_profile by noting it returns establishments rather than headquarters/admin profile, allowing an agent to route correctly among the many company_fr_* 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?

Provides explicit 'Use when' (need public establishments for a SIREN/SIRET) and 'Avoid when' (only need headquarters/administrative profile) directives, naming the alternative tool company/fr/profile. This is model guidance for when to pick this tool over its siblings.

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