Références de saisie d'une note de frais

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

Annotations already declare readOnly, idempotent, non-destructive, and the description adds valuable behavior: expense types are defined per agency, projectId/deliveryId are mandatory on each line, and the API rejects couples not imputable for the selected month. It also clarifies what is returned and that no other tool provides this data, which goes beyond the structured annotations.

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 front-loaded with the return content, then organized into clearly labeled 'Quand', 'Plutôt que', and 'À appeler AVANT' sections. Every sentence carries distinct information about when, why, and what to use it for, and the Args/Returns sections are compact and scannable.

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?

Despite the lack of an output schema, the description lists all returned referential categories and the consuming context (boond_expenses_create), which is enough for tool selection and invocation. It could be more explicit about the exact response structure or error conditions, but it covers the central prerequisites and constraints for correct use.

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 three parameters. The Args section in the description essentially mirrors the schema, with only a minor nuance ('Forcer l'agence') that repeats the schema's 'déduit de la ressource'; no additional parameter semantics are added.

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 begins with a specific verb ('Retourne') and a precise resource: the referentials needed to enter an expense report for a given resource and month, enumerating agency, currency, expense types, mileage scales, and imputable project/delivery pairs. It distinguishes itself from sibling tools by naming boond_expenses_create as the consumer and boond_application_dictionary as a non-alternative.

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 states exactly when to call the tool: systematically before boond_expenses_create, because it is the only source of expense-type codes and imputable project/delivery pairs. It also explicitly rejects alternatives: boond_application_dictionary has no expense-type table and /agencies/{id} returns only a name, concluding 'Il n'existe pas de chemin alternatif.'

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