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

Annotations only declare readOnly=false, openWorld=true, destructive=false; the description adds real behavioral context beyond that: idempotency via a stable requestId, the async nature of the call ("queued ne signifie pas terminé"), and how to poll results. Auth/permission requirements and failure modes are still unstated.

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?

Three tight sentences, each earning its place: what it does, the idempotency rule, and the return/hand-off to get_run. The most safety-relevant constraint (stable requestId) is placed immediately after the purpose.

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 execution tool with no output schema and no parameter descriptions, the description covers the essentials: trigger data, idempotency key discipline, return value shape (run ID), and the follow-up tool. Missing only preconditions such as required permissions or whether the flow must be in a particular state beyond "actif".

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 must carry parameter meaning — and it does well for requestId (stable, 8-128 chars, reuse the same key with the same data after timeout) and for input ("données JSON"). However, it never explains that the required `id` is the flow identifier, leaving the most important parameter implicit.

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?

"Lancer réellement un flow actif avec des données JSON" gives a specific verb (launch) plus resource (active flow) and the word "réellement" implicitly separates it from simulation-style siblings such as simulate_workflow. It never names that sibling explicitly, so the differentiation is inferable rather than stated.

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 concrete operational guidance: reuse the same requestId and same payload after a timeout, and follow the returned run ID with get_run. It stops short of stating when NOT to use it (e.g., prefer simulate_workflow or describe_automation first), so alternatives are only hinted at.

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