Créer un positionnement

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

Annotations already signal non-idempotence, but the description enriches this with a concrete consequence: 'rien n'empêche deux positionnements du même profil sur la même affaire.' It also clarifies that state is a dictionary ID integer rather than a label, and it specifies what the tool returns. This adds useful behavioral context beyond the structured 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, front-loaded with the core purpose, and then organized into clearly labeled sections: 'Quand,' 'Plutôt que,' bullets, and 'Returns.' Each sentence contributes distinct information, and there is no filler or repetition of the tool title.

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?

The description covers the tool's purpose, trigger, sibling distinction, non-idempotence warning, dictionary-state constraint, and return value. With full schema parameter coverage, this is nearly complete. The only minor gap is that it does not explicitly state which of the optional ID parameters are expected to be present, though the 'candidat ou ressource / opportunité ou projet' wording strongly implies the required alternatives.

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 each parameter is already documented. The description adds value by grouping the parameters semantically: 'un candidat ou une ressource' and 'une opportunité ou un projet,' which clarifies the alternative candidateId/resourceId and opportunityId/projectId relationships not made explicit in the schema. The state-ID-as-dictionary-integer point is also reinforced, though largely already present in 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 resource: 'Crée un positionnement : place un candidat ou une ressource sur une opportunité ou un projet.' It also explicitly names the sibling tool boond_positionings_update and distinguishes creation from advancing an existing positioning's state. An agent can immediately understand what this tool does and how it differs from related positionings tools.

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 'Quand' section gives the concrete trigger: 'pour matérialiser une proposition de profil au client.' The 'Plutôt que' section explicitly tells the agent to use boond_positionings_update for state advancement instead of creating a second positioning. This is clear, actionable guidance with an explicit alternative.

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