Rechercher des paiements

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds value by noting that invoiceId and companyId are kept for compatibility, that keywords support Boond-specific filter codes, and that the return is a list of matching payments. This goes beyond the structured annotations without contradicting 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 well-structured with an Args section and a Returns line, making it easy to scan. It is reasonably concise, though the parameter list partially duplicates schema information and omits some parameters, causing minor inefficiency.

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 tool has 11 optional parameters and no output schema, the description provides a high-level overview but misses key context. It does not mention the 'fields' parameter for projecting attributes, nor important filters like projectId, purchaseId, and resourceId. It also doesn't clarify that all filters are combinable. The schema compensates, but the description alone is incomplete for an agent.

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 input schema already covers all parameters with descriptions (100% coverage). The description adds meaningful semantics for keywords by explaining the special ACH/CSOC/PRJ filtering syntax, and for invoiceId/companyId by flagging them as compatibility parameters. However, it omits several schema parameters (projectId, purchaseId, resourceId, fields), even though the schema covers them.

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 'Recherche des paiements / reglements dans BoondManager' (search payments/settlements), which is a specific verb+resource. The name and title reinforce this as the search tool, distinguishing it from boond_payments_get and boond_payments_create.

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 provides some usage context, such as the special keyword codes (ACH<id>, CSOC<id>, PRJ<id>) for filtering by purchase, company, or project. However, it does not explicitly state when to prefer this tool over alternatives like boond_payments_get or mention any exclusions, leaving the selection guidance implicit.

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