start_process

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=true. The description adds that a PID is returned and that read_process_output should be used to poll output, but it does not elaborate on side effects, workspace constraints, or lifecycle cleanup.

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 short sentences with no filler. The main action and return value are front-loaded, and the polling note is a concise, valuable addition.

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?

Given no output schema, the description usefully specifies that the tool returns a PID and points to read_process_output for consuming output. It is mostly complete, though it could mention process lifecycle aspects or failure modes, but those are reasonably inferable from the annotations and sibling tools.

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?

The input schema already documents command, env, shell, and workdir with about 75% coverage. The description adds no per-parameter meaning beyond saying the command runs in the background; it correctly stays at the baseline because the schema covers most param 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 uses a specific verb and resource: 'Start a background process inside the configured workspace' and states the key result, 'return its PID.' It is distinguishable from siblings like shell_command through the explicit 'background process' framing, though it does not name alternatives directly.

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 gives a useful follow-up instruction ('Poll it with read_process_output') and the phrase 'background process' implies use for long-running work. However, it does not explicitly explain when to choose this over shell_command, process_status, or stop_process, or mention any exclusions.

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