shell_exec

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

The description discloses output ordering, error screenshot behavior, and the VM lock side effect, adding context beyond the annotations. It does not cover timeout or permission details, but the lock and output specifics are valuable transparency.

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 sentences with front-loaded purpose and a concise lock warning. Every word earns its place, no redundancy or 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?

The description covers core execution, output, and lock behavior, but omits parameter semantics for optional parameters and does not detail return format beyond ordered output. Given the tool's complexity and absence of output schema, this leaves noticeable gaps.

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?

With 0% schema description coverage, the description fails to explain any parameters. It only implies the 'command' parameter via 'Run a command', leaving cwd, timeout_ms, and screenshot_on_error completely undocumented.

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 clearly states the tool runs a command to completion and captures ordered stdout+stderr output, with a screenshot on error. This distinguishes it from interactive shell tools like shell_start and shell_read, specifying a concrete verb and resource.

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?

It provides context that the command runs to completion and that the VM remains locked until vm_unlock is called, indicating when to use it and the follow-up action. However, it does not explicitly name alternatives for interactive sessions or scenarios where this tool should not be used.

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