Run an existing job again

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

Annotations already indicate a non-readonly, non-idempotent operation. The description adds valuable behavioral context: it costs GPU time, requires explicit confirmation, and is effectively a fresh roll rather than an upscale or pixel-preserving operation. This goes beyond the structured annotations and helps the agent set expectations about side effects. It does not fully describe all side effects or return behavior, but the schema's wait parameter covers return semantics.

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 compact and front-loaded with the core behavior in the first sentence. It uses an analogy to the reroll button, a short elaboration on what that means, and then a concise second paragraph on constraints. Every sentence earns its place with no redundancy.

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 7-parameter tool with no output schema, the description is nearly complete. It gives the core behavior, the precondition about recent history, the confirm requirement, and the key variant (new_prompt). The schema covers all parameter semantics, including wait's return behavior. It could be slightly richer on what happens to the original job or how results are returned when wait is false, but not critically so.

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 100%, so the baseline is 3. The schema already thoroughly documents job_id, new_prompt, confirm, wait, speed, hd, and private. The description adds a little extra meaning for new_prompt and confirm, but it does not meaningfully compensate beyond the schema, which is already strong.

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: 'Run an existing job again' with 'Same prompt and settings, a new roll of the dice.' It also grounds the behavior in the web app's reroll button, making it clear what this tool does and setting it apart from creating a new job or varying an existing one.

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?

The description gives clear context: use this when re-running an existing job with the same prompt/settings, optionally changing just the wording via new_prompt. It also states the important precondition that the job must be in recent history and that confirm: true is required. It does not explicitly name or exclude sibling tools like vary_image, so it misses the top bar for explicit alternatives.

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