Rechercher des bons de commande

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

Annotations already declare the tool as read-only, non-destructive, idempotent, and open-world. The description adds that it returns a list and supports pagination, but these are inferable from the schema. It does not reveal any behavioral traits beyond annotations, so the added value is limited.

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 relatively concise, using a header and a bullet-style list for parameters. It covers the essential elements without extraneous text. However, the structure could be improved by grouping parameters more logically (e.g., separating filters from pagination).

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 presence of an output schema (inferred from context signals), the description does not need to detail return values. It specifies the return is a list of matching orders. All parameters are covered, and the tool's search functionality with optional filters is well explained for a read-only search tool.

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?

Input schema has 100% coverage with clear descriptions for each parameter. The description repeats this information in a summary list without adding new semantics or clarifying relationships. Since schema coverage is high, the parameter semantics dimension baseline is 3, and the description does not exceed it.

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?

Clearly states the action 'Recherche' and resource 'bons de commande' (purchase orders). The description explicitly mentions filters by company and project, distinguishing it from sibling tools like 'boond_orders_get' which retrieves a single order. The title 'Rechercher des bons de commande' reinforces the purpose.

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 indicates when to use the tool: to search for purchase orders with optional filters. It does not explicitly state when not to use it or mention alternatives, but the context of sibling tools (e.g., 'boond_orders_get' for single retrieval) allows inference. Slightly lacks explicit negative guidance.

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