process_start

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

Annotations already declare destructive, non-idempotent, and open-world behavior. The description adds lifecycle context: it returns an id and points to process_output for logs and process_stop for termination. It omits waitMs/resourceWaitMs effects, but annotations carry the safety profile.

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?

Two compact sentences, with the primary purpose front-loaded and no filler. Every clause provides actionable information.

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 5-parameter mutation tool with no output schema and poor parameter descriptions, the description covers the return id and follow-up tools but leaves parameter semantics and wait behavior unexplained. Adequate but incomplete.

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 only 20% (waitMs only). The description only implies a 'command' parameter and does not explain cwd, name, or resourceWaitMs. With low coverage, it fails to compensate.

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 clear verb 'Start' and resource 'long-running background command', with examples (dev server, watcher, long build). It does not explicitly differentiate from run_command, job_start, or pty_start among the many siblings.

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 when to use (long-running background commands) and names the follow-up tools process_output and process_stop. It does not give explicit exclusions or compare against run_command, job_start, or pty_start.

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