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

Annotations already cover read-only and closed-world, and the description adds genuinely new behavior: it renders an interactive UI in the conversation, depends on MCP Apps capability, that the couple answers inside the form, and that first names entered stay in the form. The consent for anonymized study copy is also disclosed. It does not say what the tool returns or how form completion is signalled, which keeps it below 5.

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?

Front-loaded with the action and the form contents, then prerequisites, then the negative instruction about not asking questions individually. Dense but every sentence carries information; the parenthetical about MCP Apps is slightly buried mid-sentence.

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 two-parameter UI-launching tool with full schema coverage and no output schema, the description covers capability requirement, prerequisite gathering, user interaction model, and privacy handling. Only the post-form handoff (what happens once the form is submitted) is left implicit.

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%, with both enfants and animaux documented in the schema including the 3 = three-or-more convention. The description only restates that children and pets must be collected beforehand, adding sequencing context rather than new meaning about the parameters, so baseline 3 applies.

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?

'Affiche dans la conversation le questionnaire de Qui y pense ?' gives a specific verb (afficher) and resource (questionnaire), plus what the form collects: per-task who does it and who thinks about it, the result, and anonymized-copy consent. It is clearly distinct from calculer_resultat and lister_taches without naming them, though it never states the alternative explicitly.

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?

Strong context: call it when the assistant can render a UI (MCP Apps), and only after having asked for the number of children and pets. It also gives a firm exclusion — the couple fills the form, so don't ask the questions one by one — but never names which sibling to use instead for other flows.

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