Submit one queued job

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

Annotations already flag destructive=false... rather destructive=true, non-idempotent, open-world. The description adds material context beyond them: this is a paid operation, queue submissions return only a receipt, a synchronous timeout can leave an unknown paid outcome, and there is no retry/polling. This financial/partial-failure disclosure is genuinely valuable.

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?

Four dense sentences with the core action front-loaded and no filler; each sentence carries a distinct constraint (exactness, receipt-only, timeout risk, no retry). Slightly terse phrasing borders on cryptic but is efficient.

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 destructive, paid, non-idempotent mutation tool with a rich nested schema and no output schema, the description covers the key risks (cost, receipt-only return, unknown outcome) an agent needs. It omits how to retrieve results (get_job_status) beyond stating no polling, leaving a small gap.

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 all six parameters are already documented with meaning (e.g. confirm, store_io, lifecycle ACL). The description reinforces that model_id/input must be exact rather than guessed, but adds no syntax or mapping detail beyond the schema, so baseline 3 applies.

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+resource: submitting a confirmed paid model request that has passed native input-schema validation, requiring exact model_id/input. It reads as a single-job submission distinct from batch/asset siblings, but never names run_model, generate_image, or submit_generation_batch, so the agent is not explicitly routed away from look-alike siblings.

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?

Adds constraints (exact model_id/input, no invented fields, no default selection) and warnings (receipt-only on queue, unknown paid outcome on timeout, no retry/polling), which imply how it should be used. However, it never states when to choose this over run_model or generate_image/video, or that get_job_status is the follow-up for results.

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