shell_execute

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

With no annotations, the description carries the burden well: it discloses that execution goes through a login shell, that timeout kills the whole process tree, that timeout <= 0 falls back to the default, and that stdout/stderr may be truncated. It omits the security/permission posture of executing arbitrary commands and any output-size limits, which keeps it short of a 5.

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-loaded with the core behavior and the sibling routing before any detail, then cleanly separated Args/Returns sections. Slightly longer than necessary — 'wait for it to finish' is restated by the timeout sentence — but every block earns its place.

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 supplies the return shape (exit_code, stdout, stderr, duration_s, cwd, timed_out, truncation flags), so an agent knows what to expect. Missing only side-context such as permission requirements and truncation limits for an arbitrary-code-execution tool.

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: it documents all five parameters, including the non-obvious timeout edge case (zero/negative means default, not immediate abort), ~ expansion for cwd, and env merge-over-inherited semantics. This adds meaning well beyond the bare schema types.

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 specific verb+resource ('Run a shell command on this Mac and wait for it to finish') and immediately contrasts its blocking behavior with the non-blocking sibling shell_start. An agent can distinguish it from all six siblings 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 scopes usage: 'Use this for anything that finishes within the timeout' and names the alternative ('For work that outlives the timeout (builds, installs, dev servers) use shell_start instead'). That is a clear when/when-not with the routing alternative called out.

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