Référentiels de saisie d'un CRA

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

Annotations already carry readOnlyHint, idempotentHint, and destructiveHint. The description adds useful behavioral context beyond that: the exact GET endpoint, that the response is reduced and sourced from included resources (workUnitTypesAllowed, included projects, plannedTimes), and that a resource with no imputation for the month can only enter absences. This exceeds the baseline with no contradiction.

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 longer than typical, but it is effectively structured with labelled sections ('Quand', 'Plutôt que', 'Lecture seule', 'Returns') and front-loads the main purpose. Each section carries distinct, useful information; only minor redundancy exists between the opening list and the Returns list.

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?

For a read-only reference tool with no output schema, it covers the essential ground: purpose, timing, alternative tools, response sources, and a key edge case (resource without imputation). It could be more precise about the exact response structure beyond 'texte', but the returned fields are enumerated, making it sufficiently complete.

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 coverage is 100% and already describes term, agencyId, and resourceId with types, patterns, and explanations. The description does not add parameter-specific nuance beyond what is already in the schema, so the baseline score of 3 applies.

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 resource: it returns what is needed before writing a resource's CRA for a month (authorized unit-of-work types, chargeable project/service pairs, planned schedule, existing absences). It also distinguishes itself from the sibling create/update/get tools by name, so an agent can tell it apart without opening schemas.

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?

It explicitly states when to call it ('AVANT boond_timesheets_create / boond_timesheets_update'), why (workUnitTypeReference codes are published nowhere else), and what alternative to prefer for existing timesheets (boond_timesheets_get). This is full when/when-not/alternative guidance.

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