process_start

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

With no annotations, the description carries full behavioral burden. It discloses return values (internal process ID, OS PID, initial status), PTY vs pipe behavior, and hang risks. However, it omits details on failure modes, cleanup, and interaction after start, leaving some transparency gaps.

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 efficiently structured: a front-loaded purpose statement, return value summary, then a focused PTY guidance paragraph. Every sentence adds value, and the length is appropriate for the complexity of the tool.

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 start command, the description covers the essential context: when to use, return values, and the critical PTY decision. Missing lifecycle details (how to interact later) are implied by sibling tools, so the description is reasonably complete without an output schema.

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 coverage is 100%, so the baseline is 3. The description enriches the 'pty' parameter with detailed guidance and examples well beyond the schema, but does not add value for other parameters (cwd, env, etc.) beyond what the schema already provides.

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 subprocess for interactive use, with specific examples (SSH, GDB, psql). It explicitly contrasts with one-shot commands, distinguishing its purpose from sibling tools like process_list or process_kill.

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?

Provides explicit when-to-use ('interactive programs'), when-not-to-use ('not for simple one-shot commands'), and alternative approaches ('pipe mode with --no-pager/GIT_PAGER=cat'). It also instructs to consult program_query before starting, offering clear decision guidance.

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