Créer une action

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

Annotations already declare readOnlyHint=false, so the write nature is structured data; the description adds genuine context beyond that: the mandatory dependsOn attachment, the 422 failure on missing/invalid attachment, companyId's conditional acceptance, and the API-required positioningId tied to positioning-related action types. It discloses error conditions not visible elsewhere, though it stops short of describing auth needs or side effects like counts.

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?

Four short, dense sentences, each earning its place: purpose, routing, constraint set, return. The most important scoping information is front-loaded and the constraint sentence packs the validation rules efficiently with no filler.

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 12-parameter creation tool with intricate mutual-exclusivity and conditional-requirement logic and no output schema, this description is complete: it covers the entity types, the update alternative, validation failure modes, positional requirements, and the return value (created action with ID). An agent has everything needed to call it correctly.

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 baseline is 3, but the description adds real relational meaning beyond the schema: it ties the five ID params to the dependsOn relation, states the mutual-exclusivity rule among them, clarifies that companyId is only a complement to contactId, and explains positioningId's API requirement with the exact 422 code. This is genuinely additive semantic information about parameter relationships.

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+resource ('Crée une nouvelle action … dans BoondManager') and enumerates the valid parent entities (contact, candidat, ressource, opportunité, projet). It explicitly names the sibling boond_actions_update, so an agent can distinguish create from update/delete without opening a schema.

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 routes the agent: 'Plutôt que : boond_actions_update pour compléter une action déjà enregistrée plutôt que d'en créer un doublon.' It names the alternative tool and the exact condition that should select it, plus documents hard constraints (mutual exclusivity, 422 failure). Nothing is left to inference.

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