Créer une todolist

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

Annotations only say the call is not read-only, not idempotent, and not destructive; the description adds meaningful behavior: the API does not deduplicate titles, the request body is inferred from models.todolist and is not proven on a test tenant, and record tasks cannot be created here. It also discloses the return shape (confirmation and structuredContent.id). No contradiction 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 compact, uses short sections and bullets, and fronts the core purpose before the when/alternative guidance and caveats. No sentence is redundant: every line contributes purpose, timing, risk, scope boundary, or return information.

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?

With a 100%-documented schema and an output schema present, the description still provides critical context that is not in structured fields: when to use it, that titles are not deduplicated, that the body is unverified on a real tenant, and that record-level task creation is not available. The description fully equips an agent to call the tool 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 description coverage is 100%, so the schema already explains title, tasks, profile, profileTypesOf, profileStates, and agencyIds. The description reinforces that tasks are ordered and mentions the models.todolist source, but does not add per-parameter meaning; the note about an 'agencies' relation does little to clarify the actual agencyIds parameter.

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 ('Crée') and precise object ('todolist (modèle de tâches) avec ses tâches ordonnées, applicable à un type de fiche'). It also distinguishes itself from related endpoints by clarifying that record-level tasks are not created here and by naming boond_todolists_search in the alternative guidance. This prevents confusion with boond_todolists_get, boond_todolists_search, and boond_tasks_get.

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?

It provides explicit when-to-use scenarios ('définir une checklist réutilisable') with concrete examples (onboarding consultant, préparation de facturation). It also gives a when-not-to and alternative: it warns not to rely on boond_todolists_search first because the API does not deduplicate titles, and clarifies this endpoint is not for creating record-level tasks (boond_tasks_get).

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