shell_exec_async

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

With no annotations, the description carries the full burden and does disclose key behavior: non-blocking start, immediate job_id return, and lifecycle management via shell_job. It doesn't cover output capture/buffering, resource cleanup, or permission needs, leaving some behavioral 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?

Three tight sentences, front-loading the core behavior, then use cases, then the follow-up tool. Every sentence earns its place with zero filler.

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?

No output schema exists, and the description does explain the key return value (job_id) and how to interact with it later via shell_job. Covers the essentials for an 8-param tool; only minor gaps remain around output handling and cleanup.

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 100% – cwd, env, name, login, shell, timeout_ms, and interactive are all documented in the schema. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 applies.

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 precise verb+resource+behavior ('Start a command in the background and return a job_id immediately'), which clearly distinguishes it from the foreground shell_exec and pairs it with shell_job. An agent knows exactly what this does without opening the 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?

Gives concrete use cases ('long builds, dev servers, watchers and tailing logs') and names the companion tool shell_job for reading/stopping the job. It does not explicitly state when NOT to use it (e.g., use shell_exec for short/blocking commands), but the async framing implies it.

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