Rechercher des contacts

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is covered without the description. On top of that the description usefully discloses non-obvious behavior: `fields` is an MCP-side projection never transmitted to the API, and paging beyond page 100 / pageSize 500 is refused rather than clamped. It adds some value but not deep behavioral context (e.g. default summary contents, rate limiting).

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?

Long but well front-loaded and structured: purpose and sibling disambiguation first, then bulleted use-case recipes, then the projection/pagination notes. Every block is skippable reference material for a 27-parameter tool; the only slight cost is the density of repeated filter enumeration that the schema already carries.

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 27-param, zero-required search tool with a rich output schema and full annotation coverage, the description covers the remaining gaps: it states the return shape is a paginated list, routes to boond_contacts_get for detail, and explains server-side paging limits. Nothing needed to call it correctly is missing.

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%, so the baseline is 3, but the description goes beyond restating fields by supplying cross-parameter recipes the schema states only in isolation: CSOC<companyId> keyword convention with a worked example (CSOC6420), keyword format NOM#PRENOM / CSOCid#NOM#PRENOM, the #AND# prefix operator, and the perimeterDynamic shortcut instead of supplying one's own ID. This helps an agent compose valid filter combinations.

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?

Starts with a specific verb+resource ('Recherche des contacts ... dans BoondManager avec filtres serveur') and immediately disambiguates from siblings by naming boond_companies_search, boond_candidates_search and boond_resources_search and stating what a 'contact' is (interlocuteur client, pas un profil). An agent can route correctly without reading any schema.

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?

Explicit when-to-use recipes are given for each common scenario (mes contacts via perimeterDynamic, contacts d'une société via keywords CSOCprefix, états/types, complétude, recherche par nom), plus the named alternative tools for adjacent entity types. Nothing is left to inference.

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