start_process

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

With no annotations, the description carries the burden of behavioral disclosure. It discloses that the process is backgrounded, returns a handle and pid, and streams output to a log file. This provides meaningful insight beyond what annotations would offer, though it does not cover potential failure modes or process lifecycle details.

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 sentence that is front-loaded with the core action and outcome. It efficiently conveys purpose, return values, and output handling without superfluous words.

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 main behavioral aspects and return values, but with 6 parameters and no output schema, it leaves important details unexplained (e.g., what 'confirm' does, how distro is selected, env handling). It is adequate for a high-level understanding but not fully complete for safe invocation.

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 33%; cwd, env, distro, and confirm lack descriptions. The tool description does not elaborate on any parameters, so it fails to compensate for the low schema coverage. Only command and separateStderr have schema descriptions, leaving the other parameters semantically under-specified.

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 long-running process in WSL, explicitly noting it is backgrounded. It distinguishes from siblings like run_command by highlighting the backgrounded nature and the returned handle/pid, plus the log-file output mechanism.

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 usage for long-running, backgrounded tasks and indicates how output is retrieved via read_process_output. However, it does not explicitly state when to avoid this tool (e.g., for short foreground commands) or name alternatives like run_command. The context is clear but lacks explicit exclusions.

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