Start background job

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

The description discloses key behavioral traits beyond annotations: it states the job runs asynchronously and may modify the machine or external systems. This adds context beyond the destructive/open-world hints, though it does not cover return values or follow-up monitoring.

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?

Two concise, front-loaded sentences with no filler. The first sentence states the action, and the second adds critical behavioral context.

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 essential purpose and async lifecycle but omits parameter semantics, return value information, and guidance on monitoring jobs. With sparse schema and no output schema, this is a noticeable gap, though annotations and sibling tool context partially compensate.

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%, and the description provides no explanation of box_id, command, or cwd. The description fails to add meaning beyond property names, leaving users to infer parameter purposes.

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 uses a specific verb 'Start' with a clear resource 'long-running shell job' and location 'in a Box'. It also distinguishes the tool from siblings by noting asynchronous execution ('runs independently'), which differentiates it from box_execute_command and job management tools.

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 phrase 'runs independently after this tool returns' provides clear context that this is for asynchronous, long-running tasks. However, it does not explicitly name alternatives or state when not to use it, leaving room for improvement.

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