Rechercher des candidats

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so safety traits are covered. The description adds valuable behavioral context beyond these: how to use perimeterDynamic without a user ID, the AND/OR logic for tools, the availability of a period filter with date range, and keyword type defaulting. It doesn't discuss auth needs or rate limits, but for a read-only search tool the disclosed behaviors are substantial.

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 well-structured with a one-line summary, followed by grouped bullet points that correspond to common search scenarios. It is longer than average but appropriate for a tool with 36 parameters; each bullet adds practical value, and the closing line about return type and detail tool prevents unnecessary verbosity.

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?

Given the high parameter count, the description covers the primary use cases, mentions pagination and sorting, and points to the detail tool. An output schema exists, so it need not explain return fields. It could mention pagination response metadata or error handling, but this is adequately covered by the schema and sibling tool descriptions.

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 meaning by grouping parameters into use cases and clarifying unusual formats (e.g., languages as 'langueId|niveauId', tools with '#AND#' for ET, perimeterDynamic values). It does repeat some schema info, but the high-level synopsis helps an agent understand parameter interplay without reading all 36 schema entries.

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 candidats dans BoondManager avec filtres serveur', clearly stating a search action over a specific resource with a server-side filtering mechanism. It distinguishes itself from sibling detail tools like boond_candidates_get by explicitly stating that the detail view should be obtained with that tool, reinforcing its role as a list/search endpoint.

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 scenarios: self-candidates, team perimeters, states, types, technical profile, sourcing, periods, keyword search, and geolocation. It also explicitly names the alternative for detailed retrieval ('Utiliser boond_candidates_get ou les outils d'onglets pour le détail'), giving clear when-to-use and when-to-switch guidance.

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