retry_job

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

With no annotations, the description carries the full burden but only says the job is re-queued. It does not disclose whether prior progress/outputs are reset, whether the job_id is preserved or a new job spawned, required permissions, or whether the original failure artifacts remain.

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?

One sentence, front-loaded with the action and immediately qualified by the eligible states. No filler, nothing buried.

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 one-parameter mutation with no annotations and no output schema, the agent still needs to know the post-call effect (new job id vs. same id, whether prior results survive) and error behavior on ineligible states. The definition is adequate but leaves those operational questions open.

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 coverage is 0% for the single job_id parameter, so the only semantic hint is that the id must reference a failed or canceled job. That is useful but does not document the id format or what happens if the state is wrong.

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 (put back in queue) and resource (a failed or canceled job), plus the precondition on job state. It is clearly distinguishable from siblings like cancel_job or submit_video by intent, though it never names them.

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?

"Failed or canceled" gives an explicit eligibility gate, which is genuine when-to-use context beyond the name. It stops short of naming alternatives (e.g. re-submitting via submit_video) or saying what to do if the job is still running.

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