Run Shell Command

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

Beyond annotations (destructiveHint: true), the description adds that the command is killed on timeout, returns error if user declines, and specifies shell interpretation (cmd.exe vs bash). This enriches the behavioral context.

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?

The description is well-organized with clear sections (Args, Returns, Error Handling), concise yet comprehensive, with no redundant information.

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 complex tool without output schema, it covers return values, error scenarios, approval requirement, timeout, and shell differences. All critical aspects are addressed.

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 100% schema coverage, the description still adds value by stating defaults for cwd and timeout, and the max timeout. These details are not in the schema, aiding the agent in proper usage.

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 'Execute a shell command and return its stdout/stderr,' using a specific verb and resource. It also highlights the unique requirement for interactive approval, distinguishing it from sibling tools like run_command_background.

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 explicitly states 'ALWAYS requires interactive user approval,' providing a strong usage guideline. It also covers error handling for user decline and timeout, but does not explicitly mention when not to use or list alternatives.

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