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

Beyond the annotations, the description discloses idempotency semantics (stable requestId), timeout retry behavior, async execution, and the fact that a queued state is not completion. It does not contradict the annotations: a non-read-only, open-world, non-destructive launch operation is consistent. It does not cover permissions or side effects on the agent, but adds useful context.

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 three dense sentences with the core launch action and the critical requestId rule front-loaded. Every sentence carries operational meaning. It could be slightly tighter, but there is no filler.

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 launch tool with no output schema, the description does explain that an execution ID is returned and should be followed with get_run. However, it leaves the id parameter and the expected input shape unexplained, and does not describe permissions or side effects. Adequate but with clear gaps for a 0%-coverage schema.

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 compensate. It strongly clarifies requestId semantics (stable key, reuse after timeout) and implies that input is JSON data, but it never explains the id parameter beyond the vague notion of an active agent. Partial compensation for the coverage gap.

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 concrete action: actually launching an active agent with JSON data. It is distinguishable from save_agent by the word 'réellement' and from get_run by positioning get_run as the tracking follow-up. It does not explicitly differentiate from run_task or run_flow, so it is clear but not fully sibling-aware.

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 clear operational guidance: reuse the same requestId and data after a timeout, and use get_run to track execution. It also warns that queued does not mean finished. It lacks explicit when-not or alternative-tool guidance versus run_task or run_flow.

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