Rechercher des notes de frais

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds that the tool returns a list and supports filtering by resource, project, and date range, but does not disclose additional behavioral traits such as pagination defaults, result limits, or handling of unknown fields. This aligns with the annotation profile, so an average score is appropriate.

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 concise and begins with a clear single-sentence purpose. The Args list and Returns line are logically structured and easy to scan. It omits the 'fields' parameter but overall remains well-organized and free of unnecessary detail.

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 description covers the core search purpose, filters, and return type. Since an output schema exists, the simple Returns line is sufficient. However, the omission of the 'fields' parameter from the Args list is a notable gap, and the description does not mention any search-specific behavior beyond the basic filters. Given the tool's moderate complexity, this is adequate but not thorough.

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 the schema already fully describes each parameter. The description's Args list is redundant and less precise (e.g., 'Filtrer par entité liée' groups resourceId/projectId, and 'Période' omits the exact format). Critically, it omits the 'fields' parameter that appears in the schema, potentially misleading an agent into thinking it doesn't exist. This under-delivers relative to the schema and adds minimal value.

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 the tool's purpose: 'Recherche des notes de frais dans BoondManager' (search expense reports in BoondManager) with specific filters. The verb 'Recherche' and the resource 'notes de frais' distinguish it from sibling tools like boond_expenses_get (retrieve a single expense) and boond_expenses_create/update/delete.

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 usage for searching expense reports with filters, and lists available filter dimensions. However, it does not explicitly state when to use this tool versus alternatives (e.g., 'use boond_expenses_get for a single expense'), so usage guidance is only implied, not explicitly contrasted.

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