Modifier un(e) candidat

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, covering the mutation and safety profile. The description adds valuable context beyond annotations: the partial-update semantic ('Seuls les champs fournis sont modifiés') and the return value ('Données mises à jour'). This is meaningful behavioral disclosure without violating 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 extremely concise: two sentences plus a return line. It front-loads the action with a specific verb and resource, then adds the critical partial-update detail. Every sentence serves a purpose with no filler or redundancy.

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 tool with 11 parameters, 1 required, full schema coverage, and an output schema, the description covers the core purpose, the partial-update behavior, and the return value. Annotations handle idempotency and destructive hints. It does not mention error cases or authentication, but these are not essential for a well-specified update operation, so it is nearly 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?

The input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds the key insight that only provided fields are modified, which is a parameter-level behavior not captured in the schema. This clarifies how to interpret all optional parameters and justifies a score above baseline.

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 clearly states the action: 'Met à jour un(e) candidat existant(e) dans BoondManager' (Updates an existing candidate). It uses a specific verb and resource, and explicitly mentions 'existant(e)' to distinguish from create/delete. This differentiates it from sibling tools like boond_candidates_create and boond_candidates_delete.

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 provides clear context that this tool is for updating an existing candidate, implying it should not be used for creation or deletion. It also specifies partial-update behavior ('Seuls les champs fournis sont modifiés'), which guides when and how to use it. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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