Submit a generation without waiting

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

Beyond the annotations, the description exposes the key behavioral cost: GPU time is spent and cannot be refunded, and confirm: true is required. It also states the fire-and-forget return behavior. This is valuable context the annotations do not convey, though it does not elaborate on failure modes or what the returned job id looks like.

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 short paragraphs pack in the core behavior, usage context, follow-up tools, and the critical confirmation requirement. Every sentence earns its place, and the most important fact—return immediately with the job id—is front-loaded.

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 29-parameter tool, the schema handles parameter details, and the description covers what the agent needs beyond that: the async behavior, why to choose it, what to call next, and the cost/confirmation caveat. The absence of an output schema is mitigated by the explicit statement that a job id is returned.

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?

The input schema already covers 100% of parameters with detailed descriptions, so the baseline is 3. The tool description itself does not add param-level semantics beyond repeating that confirm: true is required, which is already in the schema. It is not harmful, but it does not carry additional meaning.

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 clearly states the tool submits a generation and returns immediately with the job id, without waiting for images. It names the exact asynchronous behavior and distinguishes itself from imagine, which is the tool to prefer when you just want the pictures.

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 explicit when-to-use guidance: queue several prompts at once or use relax mode where jobs take minutes. It also names follow-up tools (wait_for_job, get_job) and the alternative tool (imagine), making the routing decision unambiguous.

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