Créer un formulaire

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

Beyond the annotations, the description adds that this is a non-idempotent write, that the request body is derived from models.form, and that the behavior has not been proven on a test tenant. It also states the exact-one-target constraint and the returned confirmation/ID, giving a clear contract for a mutation tool.

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 action, and uses labeled sections/categories for usage, body behavior, and return value. Every sentence adds information; there is 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 7-parameter create tool with annotations and an output schema, the description covers when to use it, how it relates to boond_forms_default, the body/return contract, the one-target rule, and even a reliability caveat. Nothing an agent needs to make a correct first invocation is missing, aside from the minor schema-required mismatch already noted.

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 schema already documents all seven parameters at 100% coverage, so the baseline is 3. The description adds real value by mapping parameters to model fields (template, dependsOn, validator, recipient, validateDate, remindDate) and enforcing mutual exclusion between resourceId and candidateId. However, this mutual-exclusion constraint is stated in prose while neither parameter is marked required in the schema, creating a small alignment ambiguity.

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: 'instancie un formulaire à partir d'un modèle ... pour une ressource ou un candidat', with concrete example templates. This clearly distinguishes the create operation from sibling read/prefill tools such as boond_forms_get and boond_forms_default.

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?

Explicitly gives the trigger condition ('pour lancer une campagne d'évaluation ou un bilan, formulaire par formulaire') and the preferred sibling to consult first ('Plutôt que : boond_forms_default d'abord, pour les questions et les dates attendues par le modèle'). This leaves no doubt about when to invoke this tool versus the alternative.

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