Rechercher des achats/sous-traitance

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, informing the agent that this is a safe read operation. The description adds that it returns 'Liste des achats correspondants' (list of matching purchases), but provides no additional behavioral context beyond that, such as pagination behavior, defaults, or handling of empty results. The added value over annotations is minimal.

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 exceptionally concise, using a clear structure: purpose statement, Args list, and Returns line. Every sentence contributes meaning, and the key information is front-loaded. There is no fluff or redundancy, making it easy for an agent to parse quickly.

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?

Given the read-only nature (annotations), full schema coverage, and no output schema, the description adequately covers the essential context for a search tool. It states the resource, lists the main filters, and indicates the return type. The only minor gap is not mentioning the 'fields' projection parameter in the description, but since the schema fully explains it, this is a small omission. Overall, it is sufficiently complete for its simplicity.

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?

The schema covers 100% of parameters with individual descriptions, establishing a high baseline. The description groups keywords, companyId, and projectId as 'Filtres' and page/pageSize as 'Pagination', which adds a small level of categorization. However, it omits the 'fields' parameter entirely from the Args list, and the high-level grouping does not significantly deepen understanding beyond what the schema already provides.

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 achats et sous-traitances dans BoondManager' (search purchases and subcontracting). It specifies a distinct resource and action, distinguishing it from other purchase-related tools like get/create/delete. The mention of filters and pagination reinforces the search intent.

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 does not explicitly state when to use this tool versus alternatives. It implies search usage through the verb 'Recherche' and the presence of filter parameters, but lacks explicit guidance such as 'use this to search, use get to retrieve a single item' or any exclusion criteria. This is implied rather than explicit.

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