Rechercher des contacts

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

Beyond the rich annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses non-obvious behavior: server-side filtering, paginated returns, OR-by-default with the '#AND#' trick for combining filters, the typesOf naming gotcha (⚠️ with 's'), and keyword format conventions (CSOC prefix, NOM#PRENOM). 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 front-loaded (purpose in the first sentence) and uses a scannable bullet structure organized by use case with bolded parameter names and inline code. While long, every section earns its place for a 27-parameter search API, and it avoids restating each parameter's schema description.

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 high-complexity tool (27 optional params, no required params), the description covers the essential combination patterns, sort behavior, return type, and pointer to detail tools. With annotations and output schema covering safety and return structure, the description focuses on the non-obvious semantics an agent needs to invoke the tool correctly.

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?

Although the schema covers 100% of parameters, the description adds meaning beyond schema descriptions: the 'CSOC<companyId>' convention for company-scoped searches, the 'data' shortcut for perimeterDynamic, the NOM#PRENOM format for fullName, dictionary references (setting.state.contact, setting.typeOf.contact), and cross-parameter combination patterns.

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 first sentence states a specific verb+resource: 'Recherche des contacts (interlocuteurs clients / prospects) dans BoondManager avec filtres serveur.' It clarifies the scope (client/prospect contacts) and distinguishes from sibling search tools (resources, companies, candidates), while the closing line differentiates it from boond_contacts_get by noting it returns a paginated summary list.

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 a dedicated 'Cas d'usage courants' section with concrete recipes for common scenarios (my contacts, by company, by states/types, by period, by completeness, by name). It explicitly names the alternative for detail lookup: 'Utiliser boond_contacts_get ou les outils d'onglets pour le détail' and gives parameter patterns for each context.

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