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

Annotations already establish the read-only, non-destructive, closed-world profile, so the bar is lower. The description adds genuinely non-obvious behavior: a 1,000-row cap, a bounded payload size, and the returned keys (filename, csv), which tells the agent the response is a file payload rather than rows to page through.

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?

A single front-loaded sentence leads with the action and resource, then adds return value and limits, with no filler. The semicolon-chained clauses are slightly dense but nothing is wasted.

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 no output schema, the description correctly discloses the return keys and the truncation limit, which is the most important thing an agent needs. It remains incomplete on parameter meaning and on how this export relates to the overlapping form-response tools.

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 0% across four parameters (id required, plus q, tag, status enum), so the description carries the full burden. It only alludes to 'filtres' generically and never explains what q, tag, or status filter on, nor the meaning of the required id.

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 gives a specific verb and resource ('Exporter les réponses filtrées en CSV') plus the return shape, so the agent knows this produces a CSV export rather than a list. It does not, however, distinguish itself from the many form-response siblings (list_form_responses, list_form_submissions, list_crm_form_responses, export_collection_rows), so an agent must infer the boundary on its own.

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?

'affiner les filtres si nécessaire' implies the export will truncate and that narrowing filters is the remedy, which is implicit usage guidance. There is no explicit statement of when to export versus when to call list_form_responses or get_form_response instead, which is the main gap.

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