Valider ou refuser un CRA / une note de frais / une absence

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

It goes well beyond the annotations: rejection requires user confirmation when elicitation is supported and is disabled by BOOND_MCP_CONFIRM_REJECT=0, declined confirmation returns decided:false without an API call, the operation is idempotent, and the inferred PUT route may return 404/405 that should be surfaced as-is. This is rich, non-obvious behavioral context that annotations alone do not provide.

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?

Dense and front-loaded: purpose in the first sentence, followed by when, alternatives, route risk, confirmation behavior, idempotence, and return shape. Every sentence contributes essential information; no filler or repetition of the schema.

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 mutation tool with an output schema and annotations, the description fully covers what an agent needs: decision semantics, prerequisites, route caveats, confirmation flow, idempotence, and return value shape. Nothing critical is missing.

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 the baseline is 3, but the description adds real value: it maps decision values (validate → validated, reject → rejected), explains that id is the validation id and not the document id, and notes that reason is recommended for refusals. This clarifies usage beyond the raw 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 states exactly what the tool does: 'Approuve ou refuse une validation en attente : CRA, note de frais ou demande d'absence' with the specific verbs validate/reject and the resource (validation). It also distinguishes itself from siblings like boond_validations_search and boond_validations_get, and clarifies there is no other write path in the workflow.

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 explicitly says when to use it: after boond_validations_search and document review via boond_timesheets_get, boond_expenses_get, boond_absences_get. It also tells the agent what NOT to use instead (boond_validations_get for re-reading) and that no alternative write path exists on the validation workflow.

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