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

Annotations only cover the safety/idempotency profile; the description adds the behavior that actually matters here: the work runs asynchronously, the model design step 'takes minutes', the immediate return is job_id/status 'running', and the recommended polling cadence. That is substantial context an agent cannot derive from the annotations.

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 async contract, then the polling instruction, tightly written with no filler. The trailing 'Returns:' block partially restates the earlier job_id/status point and get_status's role, so it is efficient rather than perfectly lean.

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 long-running async tool with no output schema, the description supplies the essential operational knowledge: immediate job_id return, expected duration, what get_status delivers, and the polling interval. It is only short on the parameter surface, which it explicitly delegates to generate_dataset.

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?

With 7 parameters at 0% schema description coverage, the description compensates for only one of them (it identifies `request` as plain-English and glosses the rest as 'the same as generate_dataset'). The remaining six parameters must be resolved by opening a different tool, leaving a large semantic gap even though the deferral is a reasonable strategy.

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?

States a specific verb and resource ('Start a generation in the background') and immediately differentiates itself from the synchronous sibling by noting it 'return[s] a job_id at once' while 'Arguments are the same as generate_dataset'. An agent can tell the two apart without opening either schema.

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?

Gives a clear trigger ('Use it for any plain-English `request`') and a follow-up loop ('then call get_status(job_id) every 20-30 seconds until it says done'), effectively routing to the sibling get_status. It never states an explicit when-not (e.g. when you already have a ready DDL/blueprint, prefer the synchronous path), so it falls short of full 5-level guidance.

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