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 useful behavioral context beyond annotations: it notes that results are a paginated list, that filters are server-side, and that company type must be inferred via the detail endpoint. There is no contradiction with annotations, but no additional safety or rate-limit info is given, keeping the score at 4.

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 longer than a minimal one-liner, but it is well-structured with a clear purpose line, bulleted use cases, a note, and a returns line. Every section earns its place given the tool has 22 parameters and requires substantial guidance. It could be slightly tighter, but the organization makes it scannable and effective.

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 a 100% schema description, good annotations, an output schema, and 22 parameters, the description is remarkably complete. It covers the main use cases, parameter relationships, a critical limitation (typeOf), and directs to the appropriate detail tools. No major information gap is evident.

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. The description adds meaningful value by showing common parameter combinations (e.g., perimeterDynamic: ['data'] for 'Mes comptes') and the special ID syntax (keywords: 'CSOC<id>'), which are not evident from the schema alone. It groups related parameters by use case, adding interpretation beyond the raw descriptions.

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 'Recherche des sociétés (clients, prospects, fournisseurs…) dans BoondManager avec filtres serveur', which clearly states a specific verb (recherche) and resource (sociétés), and distinguishes from the sibling get tool by noting that detail is obtained separately. It also clarifies search behavior (server filters, pagination) and a key limitation (no typeOf filter), making the purpose unambiguous.

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 'Cas d'usage courants' section provides concrete examples for common scenarios (mes comptes, états, période, recherche par ID), which is explicit when-to-use guidance. The description explicitly directs users to boond_companies_get for detail and warns about the missing typeOf filter, effectively stating when not to rely solely on this search tool.

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