Rechercher des contacts

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

Annotations already convey read-only and idempotent behavior (readOnlyHint=true, idempotentHint=true), and the description adds value by noting server-side filtering and paginated results. It also clarifies parameter-specific behavior like the '#AND#' prefix for AND logic and the 'typesOf' spelling pitfall. No contradictions 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 lengthy but well-structured with a summary line, bullet points for common use cases, and a closing note about return values. Each bullet adds unique value (examples, pitfalls, syntax details) necessary for a 27-parameter tool, so the length is justified. It is front-loaded with the core purpose and then organized logically. It loses a point for not being tighter, but the complexity warrants the detail.

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 tool with 27 optional parameters, rich schema descriptions, and an output schema, the description gives comprehensive guidance on when/how to use it, including parameter interactions, examples, and sibling tools for details. It covers all major filter categories (perimeter, states, period, completeness, keywords) and even returns a pagination hint. There is no obvious missing piece.

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%, but the description goes far beyond by explaining real-world usage: examples like 'keywords: "CSOC6420"' for company contacts, 'perimeterDynamic: ["data"]' for 'mes contacts', and format details like 'fullName' using 'NOM#PRENOM'. It also disambiguates tricky parameters (e.g., typesOf vs typeOf, AND/OR logic) making it exceptionally helpful for an agent.

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 clear statement: 'Recherche des contacts (interlocuteurs clients / prospects) dans BoondManager avec filtres serveur.' This names the exact resource (contacts) and distinguishes it from sibling search tools by explicitly focusing on contacts and mentioning server-side filtering. The detailed use cases further reinforce its specific purpose.

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 provides explicit common use cases (e.g., 'Mes contacts', contacts of a company, states/types, period, completeness) and closes with a direct pointer: 'Utiliser boond_contacts_get ou les outils d'onglets pour le détail.' This tells the agent when to use this search tool versus alternatives for detail retrieval. However, it does not contrast with other search tools (e.g., companies_search), so it is not a perfect 5.

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