colab_job_start

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

No annotations are provided, so the description carries the full burden, and it does disclose key traits: execution is non-blocking, a job id is returned, and 'Jobs die if the VM is stopped' warns about job lifetime. It omits anything about working directory, environment, permissions, or how to cancel, but the async and persistence behaviors are the material ones.

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?

Three compact sentences, front-loaded with the action and example, then usage guidance, then the lifetime caveat. Every sentence adds information; 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?

An output schema exists, so return-value details are covered, and the description adequately explains the async lifecycle and how to poll. The remaining gap is the two optional parameters (name, session), which are silent in both schema and description.

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 0%, so the description must compensate, and it only illustrates the 'command' parameter with an example. The optional 'name' and 'session' parameters are completely unexplained — an agent cannot tell whether 'session' targets a specific VM/session or what 'name' is used for.

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 and resource ('Start a shell command in the background on the VM') plus the return artifact ('return a job id'). The background/async nature meaningfully differentiates it from synchronous siblings like colab_exec and colab_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?

'Use for anything longer than a few minutes' gives a clear positive trigger for this tool versus short-lived synchronous execution, and it routes the agent to colab_job_status / colab_job_logs for follow-up. It stops short of naming the tool to use instead for short commands (e.g. colab_exec), so the exclusion is implied rather than explicit.

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