Rechercher des sociétés

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true and destructiveHint=false. The description adds valuable context beyond these: pagination limits (pageSize 1–500, page 1–100 with refusal beyond), the fields projection that is never sent to the API and replaces the summary, and the dictionary-based filter semantics. No contradiction with annotations.

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 densely packed with structured sections (alternative, use cases, sorting, note, returns, fields, pagination). Each sentence carries functional value and is front-loaded with purpose. Slightly verbose given the 22-parameter surface, but nothing is filler.

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?

This is a 22-parameter tool, yet the description covers the core decision (what it searches, when to use it), the critical limitation (no typeOf filter), return type (paginated list) with the correct detail tool reference, pagination boundaries, and the unusual fields-projection behavior. With an output schema present, return value documentation is not needed. No meaningful gap remains.

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 the baseline is 3. However, the description adds substantial meaning beyond the schema: the compound usage of period with startDate/endDate, the semantics of perimeterDynamic as a shorthand ('data' = my own data), the special keywords format 'CSOC<id>' for targeting a company by ID, and the fields projection behavior (unknown names ignored). This meaningfully exceeds schema-only documentation.

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 states a specific action ('Recherche des sociétés'), the resource (companies in BoondManager), and the scope (clients, prospects, fournisseurs) with server-side filters. It explicitly distinguishes itself from the sibling boond_contacts_search for individuals, so an agent can differentiate the two without ambiguity.

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?

The description names the direct alternative (boond_contacts_search for physical persons) and gives conditional guidance. It enumerates common use cases with concrete parameter recipes (perimeterDynamic for 'mes comptes', states with dictionary setting.state.company, keywordsType variants), covers sorting, and explicitly warns that there is NO typeOf filter — the type must be inferred via boond_companies_get. This is complete routing and usage guidance.

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