start_process

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

With no annotations, the description carries the burden of disclosure. It mentions returning the PID and log path, which is useful, and indicates the process runs in the background. However, it does not state side effects, permission requirements, or that the process will continue after the call. The phrase 'FULL-ACCESS tool' is vague and lacks detail.

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 front-loads the core action and return values. However, the trailing 'FULL-ACCESS tool.' adds little value and could be seen as filler, slightly reducing the score from a perfect 5.

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 tool starts a background process, which has significant operational implications (lifecycle, checking status, cleanup) that are not addressed. The description does mention the return values (PID and log path), and an output schema exists, but the overall context is incomplete given the complexity and the presence of related process management siblings.

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 conceptually references the 'command' parameter but does not explain cwd, shell, or environment, leaving the agent without guidance for these fields. The description adds minimal parameter semantics.

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's function: starting a long-running command in the background and returning its PID and log path. This is specific and distinguishes it from sibling tools like run_command (foreground) and list_processes/terminate_process (management).

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 'long-running' and 'in the background' implies usage for asynchronous tasks, but it does not explicitly mention when not to use it or name alternatives like run_command for foreground tasks. The context is present but at an implied level.

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