process_start

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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds real lifecycle context: scheduler-coordinated startup, independent execution under ProcessManager ownership, no timeout, and closed stdin for agent CLIs. It does not cover failure behavior or what 'allowlisted' actually permits, leaving a modest gap.

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?

Four dense sentences, front-loaded with purpose and return value before lifecycle and the command_run alternative. Every sentence carries actionable information, though the coding-CLI note is a touch long.

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 mutation tool with no output schema and existing annotations, the description covers lifecycle, polling/termination siblings, and the timeout contrast to command_run. Missing parameter-level detail (cwd/args) is the main shortfall, but the safety and lifecycle picture is otherwise complete.

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 25% (only the nested 'agent' field is documented), yet the description never explains command, args, or cwd semantics. The coding-CLI example hints at how args are used, but it does not compensate for the undocumented 75%.

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?

States a specific verb+resource ('Start a long-running allowlisted local process') and the immediate return value (its id). It also distinguishes itself from command_run by naming the 240000 ms cap that forces the switch, so an agent can differentiate it from siblings without opening schemas.

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?

Gives explicit routing rules: use it for runs that may exceed command_run's timeout, then poll process_output and terminate with process_kill. It even adds a conditional usage note for coding-agent CLIs (closed stdin, use streaming output flags), which is prescriptive guidance an agent could not infer.

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