Rechercher des achats/sous-traitance

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

Annotations cover readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, which already tell the agent this is a safe read operation. The description adds minimal behavioral context beyond this—it notes pagination behavior and return format, but doesn't disclose things like default sorting, result limit behavior, or whether unfiltered searches are allowed/permitted in the open world.

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 and organized with a clear Args/Returns structure. However, it includes docstring-style 'Args:' and 'Returns:' formatting that's somewhat redundant with the schema's per-parameter descriptions. Still, it's efficient and front-loads the core purpose.

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?

This is a relatively simple list/search tool with good annotations and full schema coverage, and the output format is straightforward. The description covers the basics adequately. However, it could be stronger in defining the search scope semantics (does it search across all companies/projects globally or scoped?) and clarifying how it relates to the many sibling purchase-related tools. The 'fields' parameter behavior is only in the schema.

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 documents all 6 parameters. The description adds a brief categorization (keywords, companyId, projectId as filters; page, pageSize as pagination), which is useful but largely restates what the schema already conveys. The description does not mention the 'fields' projection parameter at all, leaving it to the schema only.

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 purpose: 'Recherche des achats et sous-traitances dans BoondManager' (search for purchases and subcontracting). The title 'Rechercher des achats/sous-traitance' reinforces this. However, it doesn't distinguish itself from sibling tools like boond_companies_purchases, boond_projects_purchases, or boond_purchases_get, which clearly relate to the same domain.

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 lists the filter parameters (keywords, companyId, projectId) and pagination, and states 'Returns: Liste des achats correspondants', but provides no guidance on WHEN to use this search tool versus the many sibling tools like boond_companies_purchases, boond_projects_purchases, or the get/create/delete siblings. There's no mention of exclusions or alternatives.

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