start_process

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

No annotations exist, so the description carries full burden. It fails to disclose behavioral traits such as whether the process runs in background, potential side effects, permission requirements, or that it may block if 'wait=true'. The sole mention of 'wait' is insufficient.

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 very short (one sentence plus a hint), but it is not overly verbose. However, it sacrifices completeness for brevity, so it is not optimally structured. It earns a 3 for being concise but lacking necessary detail.

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?

Given that an output schema exists but is not described, and the input has 4 parameters with only 1 covered, the description is incomplete. The agent would need to infer behavior from the schema alone. The description does not sufficiently complement the structured data.

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 explains the 'wait' parameter. No details are given for 'file_path', 'arguments', or 'cwd', leaving the agent without semantic understanding of these parameters beyond their schema names.

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 starts a process on the guest, which is a specific verb and resource. It distinguishes from siblings like 'health_check' or 'reboot', but does not differentiate from similar tools like 'run_cmd' or 'run_ps'. However, the core purpose is clear.

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 only hints at using 'wait=true' to wait for exit code, but provides no guidance on when to use this tool over alternatives like 'run_cmd' or 'open_shell'. No exclusions or contextual indicators are given.

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