run_job

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

Beyond the readOnly/destructive annotations, it discloses async behavior (returns a job id at once), that the job outlives the chat and Takes, that progress surfaces in the session's Jobs row, and the shell/cwd the command runs in. This is rich lifecycle context the annotations cannot convey.

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?

Dense and front-loaded: the primary action and its threshold lead, followed by lifecycle and execution details. Every sentence carries information with no filler.

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?

With no output schema, the description still covers the return value (job id), the job lifecycle, and how to await completion. Nothing essential for correct invocation is missing.

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%, so the baseline is 3; the description adds real meaning for 'cmd' by stating it runs in zsh inside the session folder. It adds little for label/outputs/session beyond what the schema already documents.

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 precise verb+resource ('Run slow work') and enumerates concrete cases (render, Demucs, Whisper, matting, commands over ~30s), distinguishing it from get_job/stop_job and from ordinary Bash execution. An agent immediately knows this is the async long-work launcher.

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?

Gives an explicit threshold ('over about 30 s') and a hard exclusion ('never as a background Bash job or with sleep'), which is exactly the when/when-not guidance an agent needs. It also points to the wait mechanism via the result note.

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