shell_start

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

No annotations are provided, so the description carries the full burden and does well: it discloses background execution, output buffering as it arrives, and that the operation is non-blocking with a returned job id. It does not cover environment/permission caveats or what happens if the command exits immediately, but the core behavioral model is clear.

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?

Front-loads the core purpose, then the buffering/lifecycle sentence, then compact Args and Returns blocks. Every line is useful; the Args/Returns sections restate the schema property names but earn their place given the 0% schema coverage.

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 job-launching tool with no output schema, the description provides the return fields (job_id, pid, command, cwd), the background/buffering semantics, and the lifecycle routing to siblings. Nothing an agent needs to call it correctly is missing.

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, and it does: all three parameters are documented (command, cwd with its home-directory default, env as extra variables). Slightly less than a 5 because per-parameter types/format nuances (e.g., env key/value semantics) are not spelled out.

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?

Specific verb+resource: starts a long-running command in the background and returns a job id. The name and sibling set (shell_execute, shell_job_*) make the async/background distinction explicit, so an agent can tell it apart without opening a schema.

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?

Explicitly states when to use it (builds, installs, test suites, dev servers that would blow shell_execute's timeout) and names the follow-up tools for the full lifecycle: shell_job_output for reading, shell_job_wait for blocking, shell_job_kill for stopping. Both the trigger condition and the alternative are given.

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