Rechercher des bons de commande

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the agent knows this is a safe, read-only, non-destructive operation. The description adds the 'Returns: Liste des bons de commande correspondants' behavior and pagination context. It doesn't disclose response format details, but the output schema exists. The description adds modest value beyond annotations but doesn't contradict them.

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 - a title line, a short summary sentence, an Args list, and a Returns line. It's reasonably structured with the Args list mirroring the schema. The 'Recherche des bons de commande' opening sentence is somewhat redundant with the title but acceptable. No wasted sentences.

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 tool has 6 parameters, a 100% schema coverage, and an output schema exists. The description is adequate for a search/read operation given the rich annotations and schema. It covers the purpose, key filters, and return type. However, it doesn't explain the 'openWorldHint' behavior or how the fields projection interacts, and the Returns line is thin. For a search tool with good annotations, this is acceptable but not exceptional.

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 coverage is 100%, so all 6 parameters are documented in the schema itself with descriptions (page, fields, keywords, pageSize, companyId, projectId all have descriptions). The description lists keywords, companyId/projectId, and pagination, but adds minimal meaning beyond 'search terms', 'filter by linked entity', etc. Baseline 3 is appropriate since schema does the heavy lifting; the description adds a small amount of framing.

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 the tool searches for purchase orders (bons de commande) in BoondManager with filters by company and project. It's specific about the verb+resource (search orders) and mentions the key filters. However, it doesn't explicitly distinguish itself from the many sibling search tools or clarify how this differs from related queries (e.g., boond_projects_orders, boond_contacts_orders), though the resource is clearly defined.

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 mentions filters by company and project but doesn't provide explicit guidance on when to use this vs alternatives. It doesn't say 'use this to list all orders' vs 'use boond_orders_get for a single order' or differentiate from the many other search tools. The usage is implied (search orders with optional filters) but no when-not/alternatives guidance is given.

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