Rechercher des notes de frais

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

Annotations declare readOnlyHint=true, openWorldHint=true (filters optional, all results returned), idempotentHint=true, destructiveHint=false. The description adds the date range and entity filter semantics beyond these. It also notes pagination exists. However it doesn't disclose behaviors like default page size (30), max caps, or what 'standard summary' means in the projection field description — though these appear in schema rather than description.

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 — one sentence on purpose plus an Args list restating parameters. It front-loads the key purpose. The Args block is somewhat redundant with the schema (100% coverage), but not verbose. Efficient enough for the coverage it provides.

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?

Tool has output schema, rich annotations, and full schema parameter documentation. The description completes the picture with the filtering dimensions available. Given annotations already provide safety/idempotency context, the description is adequate — though it could note that all filters are optional and combinable, which the openWorldHint partially covers.

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 description coverage is 100%, so all 8 parameters are described in schema. The description restates keywords, resourceId/projectId, startDate/endDate, and page/pageSize but adds no meaning beyond what schema already provides (formats, defaults, ranges). The fields projection parameter is documented in schema with useful semantics about summaries and ignored unknown names.

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 'Recherche des notes de frais dans BoondManager avec filtres par ressource, projet et période' — a specific verb (rechercher/search) plus resource (notes de frais) and filter dimensions. It clearly distinguishes from get/create/update/delete sibling tools focused on individual expense records, though sibling search tools like boond_timesheets_search share identical naming conventions.

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 implies when to use it — for searching expense notes with filters — and the search-vs-get distinction is inferred from sibling names. However there's no explicit when-not-to-use guidance or alternatives named, and no exclusion statements distinguishing it from boond_resources_expenses_reports (which reports expense data per resource).

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