Rechercher des rôles

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

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, covering the safety profile robustly. The description adds the pagination behavior and return format (list with ID, name, main details). It does not disclose things like max pageSize (schema says 100 but annotations... actually schema says max 100 for page, 500 for pageSize) or any rate-limit or auth requirements, but with strong annotations the bar is lower.

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 compact with a clear docstring structure listing args and returns. It's reasonably front-loaded with the purpose statement. Slight redundancy exists: defaults are repeated in both the description and the schema (page default 1, pageSize defaults differ—description says 20, schema says 30, a minor discrepancy worth noting).

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 read-only search tool with an output schema, 100% schema coverage, and robust annotations, the description covers the key aspects: purpose, keyword semantics, pagination, and return format. The minor default value discrepancy (pageSize default 20 in description vs 30 in schema) is a small issue, and the 'fields' projection param is undocumented in the description, but overall it's fairly complete for this tool class.

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 baseline is 3. The description adds value by listing what keywords can include (nom, email, compétences), which helps the agent understand the keyword field's semantic range. It also documents pagination defaults. However, the description does NOT mention the 'fields' projection parameter at all, which is present in the schema but absent from the description—a gap, though the schema describes it well.

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 clearly states it searches for roles (rôles) in BoondManager by keywords with pagination. It distinguishes from siblings like boond_roles_get (single-fetch) and search variants on other entities (companies, candidates, etc.). However, it doesn't explicitly name the get sibling as the alternative for single fetch, which would strengthen sibling differentiation.

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 states it searches by keywords with pagination, which clearly implies the usage context (finding roles). However, it doesn't explicitly say when NOT to use this and instead use boond_roles_get, nor discuss alternatives. For a search tool among many similarly-named search tools, generic guidance is implied but no explicit exclusions or alternatives are given.

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