task_run

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: the sandbox environment (ACL/bwrap/sandbox-exec), the return value (job directory), and side effects (writes lock=pid:startSec and EXIT:<code>). This goes beyond a simple 'runs a command' but does not explain timing or error handling fully.

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 a single, well-structured sentence that front-loads the primary purpose and packs in return and side-effect information without wasted words. Every phrase earns its place.

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?

For a simple 2-parameter tool with no output schema, the description covers the core action, environment, return value, and completion signaling. It could mention integration with sibling tools (e.g., use task_wait after) or clarify async behavior, but it is largely complete for its complexity.

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 only 50% (the required 'command' is described, but optional 'label' is not). The description adds no parameter-level detail and does not compensate for the missing label semantics. It only reinforces that 'command' is executed, which the schema already states.

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 'Run' and identifies the resource ('command inside the evidence-protected sandbox runner'). It clearly distinguishes from sibling tools by focusing on execution, while siblings handle waiting, output, kill, etc.

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 this tool is for starting a command, but it does not explicitly state when to use it versus alternatives like task_wait or task_output. No explicit exclusions or 'when not to use' guidance is provided, so it relies on context from sibling names.

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