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

Annotations already declare readOnlyHint=false and openWorldHint=true, and the description goes beyond them by disclosing the asynchronous execution model, the jobId return, and the required follow-up poll via get_site_project_job. It also explains the degraded behavior when no generator exists. It does not cover idempotency or duplicate-request behavior, which matters for a tool that launches background work.

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 output contract and follow-up tool are front-loaded in the first clause, then the parameter modes, then the alternative. Every clause carries information, though the language mixing and compressed phrasing ('Sans générateur, un modèle peut être préparé pour édition') make it denser than needed.

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 an async job-launching tool with no output schema, the description correctly covers the return handle and the polling path. However, with five parameters at 0% schema coverage and no annotation detail on side effects, the missing explanation of requestId and expectedProjectVersion leaves an agent likely to call it with a wrong or reused version and get an avoidable failure.

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%, so the description carries the full burden, yet it only explains templateId and proposalId. The three required parameters — projectId, requestId (clearly an idempotency key given its pattern and length bounds), and expectedProjectVersion (an optimistic-concurrency token) — are left completely ambiguous.

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 states a specific action and resource: request a proposal from the background 'Outil' generator, and it names the return value (jobId) and the follow-up tool (get_site_project_job). It also distinguishes the two input modes (templateId = starting point, proposalId = proposal to correct), which separates it from submit_site_proposal. Mixed French/English wording and internal jargon ('Outil', 'MonAssocie') cost it the top score.

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 gives conditional guidance for both optional parameters and names an alternative path (compose with submit_site_proposal) along with the fallback when no generator is available. What is missing is an explicit statement of when NOT to call it (e.g. when a job is already in flight) and any prerequisite that a site project must exist.

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