Run project command

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

The description adds crucial behavioral context beyond the annotations. It warns about high privilege, explains that no shell is inserted, and notes the executable can access paths outside the structured root. It also conveys the asynchronous nature by mentioning it returns an ID immediately, which is complemented by the annotations' destructive hint and openWorldHint. There is no contradiction.

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 efficient and well-structured: the main action is stated in the first sentence, followed by a concise security warning and explicit pointer to related tools. Every sentence adds value and there is no fluff.

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?

The description covers the action, security context, and follow-up tools, and thanks to the output schema, return values are not required. However, with 7 parameters and zero schema descriptions, the lack of parameter explanations leaves a significant gap. An agent cannot confidently supply correct values for fields like step_id or workflow_id without additional 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 description coverage is 0%, so the description must compensate. It only hints at the meaning of 'argv' ('argv-based command job') but fails to explain other parameters such as project, cwd, timeout_seconds, step_id, workflow_id, and attempt. An agent would have to guess the purpose of several parameters without any 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 tool 'Start an argv-based command job and return its ID immediately.' This is a specific verb and resource, and it distinguishes the tool from siblings like run_tests or codex jobs by focusing on argv-based command execution. The reference to 'No shell is inserted' further clarifies its nature.

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 explicitly states when to use the tool: 'Use it only under the explicit policy returned by get_permissions.' It also names the follow-up tools, 'Use get_job for output and cancel_job to stop it,' providing clear guidance on the workflow. This effectively routes an agent to the correct sequence.

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