jobs_runs_repair

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

The description indicates a mutation operation ('re-run'), consistent with readOnlyHint false. It adds context about optional task re-execution but does not disclose other behavioral aspects like permission requirements, side effects on run history, or rate limits. Annotations provide the safety profile, so the description adds moderate value.

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 a single concise sentence covering the core action and optional specificity. It is efficient but lacks any structural elements like separate sections or bullet points. Still, it is not verbose.

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?

Given the tool's complexity (5 parameters, output schema present, concept of chained repairs with latest_repair_id), the description is too brief. It does not explain the repair concept, chaining behavior, or the meaning of parameters like rerun_all_failed_tasks. The output schema exists but the description could still provide more context.

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 60% (descriptions for 3 of 5 parameters). The description only implicitly references 'specific tasks' (rerun_tasks) and does not add meaning to other parameters like run_id, rerun_all_failed_tasks, latest_repair_id, or job_parameters. The description adds little beyond what the schema already provides.

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 action ('re-run'), the resource ('a failed run'), and optional specificity ('optionally only specific tasks'). It distinguishes from sibling tools like jobs_runs_cancel or jobs_run_now by focusing on repairing failed runs.

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?

No guidance on when to use this tool vs alternatives. There is no mention of when not to use it, prerequisites, or comparison to related tools like jobs_run_now or jobs_runs_cancel. The agent is left to infer context from the tool name alone.

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