run_command

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

No annotations are provided, so the description carries the full burden. It discloses default shell (PowerShell), default timeout (30 seconds), return of both STDOUT and STDERR, and a clear warning that dangerous commands execute. This goes beyond basic expectations and informs the agent about important constraints. It does not cover details like exit codes or failure behavior, but the description's warning is a notable transparency benefit.

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 concise and front-loaded with the main action. It uses a short list of use cases and a warning, all within four sentences. Every sentence contributes valuable information without redundancy. The structure is clear, with the warning placed at the end for emphasis.

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 tool with 4 parameters, no annotations, and no output schema, the description covers the core operational details: shells, timeout, stdout/stderr, and safety warning. The main gap is not referencing the sibling run_command_long, which is directly relevant for extended timeouts. Despite this, the description is sufficiently complete for an agent to select and use the tool correctly for the majority of cases.

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?

The input schema already provides descriptions for all parameters (100% coverage), including examples and defaults. The description adds minimal extra meaning beyond the schema, mainly emphasizing that shell can switch to Git Bash/WSL for Unix commands and that the timeout is configurable. This is helpful but does not significantly elevate above the schema baseline, so a 3 is appropriate.

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 executes a shell command on the local Windows PC and returns output. It lists specific use cases (npm, pip, git, network diagnostics) and explicitly differentiates from other sibling tools like file_read or sys_info. The purpose is unambiguous and uses a specific verb+resource construction.

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?

The description provides strong context for when to use the tool: 'Use this tool to run any CLI command' with examples. It also gives clear shell selection guidance ('Use PowerShell unless the command is Unix-specific' is in the schema, but description reinforces it). However, it does not explicitly mention alternative tools like run_command_long or state when to prefer them, so exclusions and alternatives are partially covered.

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