Rechercher des validations

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety profile is established. The description adds the API requirement that startMonth and endMonth are mandatory (though schema already marks them required, the description emphasizes it's an API constraint). It also adds the keywords prefix convention (TPS/EXP/ABS/COMP mapping to CRA/frais/absence/ressource) which is useful behavioral context. 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 reasonably compact with a French intro line, an alert about the required months, an Args section enumerating params, and a Returns line. The Args section duplicates much of what the schema already documents, which is slight waste, but overall it's efficiently organized and front-loaded with purpose. Minor redundancy in listing enum values already in schema.

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 search tool with 100% schema coverage, readOnly/annotations, and no output schema, the description is mostly adequate. It doesn't describe the return format (beyond 'Liste des validations'), pagination behavior (page/pageSize params exist in schema but not explained in description), or how fields projection works in behavior. For a 10-parameter tool, this is acceptable but could explain the validation workflow context more.

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 all 10 parameters are described in the schema. The description adds marginal value: it restates startMonth/endMonth as required (redundant with schema) and lists documentTypes/validationStates enum values (already in schema). It does add the keyword prefix mapping (TPS= CRA, EXP= frais, ABS= absence, COMP= ressource) which the schema also includes. Net: minimal additive value over schema, hence baseline 3.

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?

Clear verb+resource: 'Recherche des validations en attente' (search for pending validations) in BoondManager, listing the document types covered (absences, expense reports, timesheets). It distinguishes from sibling tools like boond_validations_get (get single) and the many resource-specific report tools (boond_resources_times_reports, etc.) by being an aggregated cross-resource search for validations.

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 notes startMonth/endMonth are required by the API (⚠️ notation), which is helpful context. However, it does not explicitly provide when-to-use vs alternatives, nor exclusions (e.g., when to use boond_resources_times_reports vs this tool for a specific resource's validations). The sibling list contains many validation-adjacent tools that aren't differentiated.

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