Modifier une référence (expérience pro)

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

With annotations already providing readOnlyHint=false, idempotentHint=true, and destructiveHint=false, the description adds substantial beyond-annotation context: the read-modify-write mechanism, that only explicitly provided fields replace values while others remain intact, the return behavior (confirmation + republished technical dossier), and the error case for an unknown referenceId. No contradiction with 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 compact and well-labeled with clear sections (purpose, when, rather-than, use case, returns). Each sentence earns its place, though it is slightly long for a 10% weight dimension; the structure compensates by making it 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 having no output schema, the description explains what is returned (confirmation and republished technical dossier) and the error format (isError: true with list of present IDs). Combined with the annotations (idempotency, non-destructive), all information an agent needs to invoke this mutation tool correctly is present.

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 fully documents all 11 parameters including edge-case warnings (leading-zero months rejected). The description adds modest value by name-dropping startMonth/startYear/endMonth/endYear as typical fields to complete, but the schema already carries the semantic load. Baseline 3 is appropriate.

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?

States a specific verb and resource ('Met à jour une référence existante' via read-modify-write on /resources/{id}/technical-data) and explicitly differentiates from the sibling boond_resources_reference_create. The partial-update semantics clarify exactly what the tool does versus alternative operations.

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?

Explicit 'Quand' section states when to use (correcting an existing work experience), a 'Plutôt que' section names the sibling create tool as the alternative, and a concrete typical use case (completing date fields without touching title/company/description) tells the agent exactly when this tool is the right choice.

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