rerun_agent_run

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

With no annotations, the description carries full burden. It discloses key behaviors: state reset, re-enqueuing, force-cancelling if running, and error on completed runs. This is adequate, though it could mention idempotency or side effects.

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 extremely concise, using two well-structured sentences to convey purpose, behavior, and edge cases with no redundant information.

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 simple operation (one parameter, no output schema), the description fully covers all necessary aspects: what it does, when it works, and when it fails. No gaps remain.

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 100% with a clear 'Run UUID' description. The tool description adds context that the run must be in a specific state, exceeding the schema alone. This provides meaningful additional guidance.

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 verb (rerun) and resource (Rolli Agent run), specifying the allowed states (failed, waiting, or stuck). This distinguishes it from sibling tools like start_agent_run and cancel_agent_run.

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 implies when to use (for non-completed runs) and when not to (returns 422 if already completed). However, it does not explicitly contrast with alternatives like cancel_agent_run or start_agent_run, though the context is clear.

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