Rechercher des validations

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: that `fields` is a projection handled MCP-side and never sent to the API (unknown names ignored), and that pagination limits are enforced (pageSize 1–500, page 1–100, with refusal if exceeded). These details go beyond the annotations and schema, providing practical call constraints.

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 and front-loaded with the core purpose. It uses a clear hierarchy: a one-line summary, a 'Quand' section, a 'Plutôt que' section, a warning, a returns note, and two bullet points for fields and pagination. Each sentence earns its place, with no fluff; the warning symbol adds emphasis without redundancy.

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?

The tool has 10 parameters but 100% schema coverage, and the description adds crucial context for fields and pagination along with explicit usage guidance. It does not describe the structure of returned validation objects (there is no output schema), leaving some ambiguity about the 'résumé standard' format. However, for a search tool with well-documented schema, this is a minor omission; the description is sufficiently complete for correct invocation.

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% with each parameter described, so baseline is 3. The description adds extra meaning: for `fields` it explains the MCP-side projection behavior and that unknown names are silently ignored, and for pagination it clarifies the refusal semantics ('au-delà : refus, affiner les filtres'). It also reinforces that startMonth/endMonth are API-required. These additions improve param understanding beyond 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 states a specific verb and resource: 'Recherche des validations en attente' (search for pending validations) in BoondManager, and clarifies the scope (absences, expense reports, timesheets). It explicitly distinguishes itself from sibling tools like boond_absences_search, boond_expenses_search, boond_timesheets_search by noting it returns validation workflow rather than content. This gives the agent a clear, unambiguous 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 includes a 'Quand' (when) section stating it is for listing what awaits managerial validation over a month range, and a 'Plutôt que' (instead of) section naming alternative tools and the difference in outcome. This gives explicit when-to-use guidance and alternatives, leaving no ambiguity about selection.

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