Créer une action

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

Annotations indicate a mutating but non-destructive tool. The description adds behavioral details beyond annotations: it explains the mandatory 'dependsOn' relationship, the error condition for missing positioningId (422), and the flexibility of typeOf (dictionary or override). No contradictions 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 well-organized with an introductory sentence and a labeled args list. It is slightly verbose but every sentence provides valuable information. Could be tightened, but overall efficient.

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?

Given 12 parameters and no output schema, the description covers the essential aspects: entity types, parameter roles, and a special error case. It lacks explicit mention of return format (though it says 'Returns: L'action créée avec son ID'). For the complexity, it is fairly 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?

Schema coverage is 100%, and the description adds significant meaning beyond schema descriptions. It clarifies the dependsOn relation, the exclusivity condition for companyId, the requirement for positioningId for specific action types, and the fallback for typeOf. This enriches the agent's understanding.

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 verb 'Crée' (creates) and the resource 'action' with specific types (appel, email, RDV, note), and distinguishes it from sibling tools like boond_actions_search or boond_actions_delete by focusing on creation. The mention of 'rattachée à un contact, candidat, ressource, opportunité ou projet' adds specificity.

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 implies when to use (creating an action attached to an entity) but does not explicitly state when not to use or provide alternatives among siblings. It does offer some contextual guidance, e.g., that positioningId is required for certain action types and companyId is complementary to contactId.

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