Références de saisie d'une note de frais

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond that: returned data is agency-scoped, expense types carry VAT, and projectId/deliveryId pairs must be imputable for the target month. It doesn't disclose error or availability behavior, but that is a minor gap for a read-only lookup.

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 main content is front-loaded in the first sentence and the later sections are labeled (Quand, Plutôt que, À appeler AVANT, Returns), which helps an agent scan it. It loses the top mark because the call-before-expenses_create point and the boond_application_dictionary caveat are each stated twice.

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?

There is no output schema, but the description compensates by enumerating the reference categories returned and stating that they are what must be copied into boond_expenses_create. It stops short of describing the exact response shape, but for a read-only precondition lookup this is largely sufficient.

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 resourceId, term, and agencyId including the note that agencyId is optional and inferred from the resource. The description echoes 'ressource et mois donnés' but adds no new parameter-level semantics beyond the schema.

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 opens with a specific verb and object: 'Retourne les référentiels nécessaires pour saisir une note de frais pour une ressource et un mois donnés', and enumerates exactly what those references are (agency, currency, expense types, mileage scales, project/delivery pairs). It clearly positions the tool as the lookup/prefill step for boond_expenses_create rather than a general search or mutation.

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 gives an explicit trigger condition ('systématiquement avant boond_expenses_create') and explicitly rules out alternatives ('boond_application_dictionary ne publie aucune table... /agencies/{id} ne renvoie qu'un nom. Il n'existe pas de chemin alternatif.'). This is strong when-to-use vs not-to-use guidance.

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