Automate project tasks by executing shell commands (PowerShell/sh). Use this feature to run necessary scripts during build, check, and deployment while adhering to safety constraints.
Run a shell command (PowerShell on Windows, sh elsewhere). Destructive ones (force-push, deleting tags/repos/releases, unpublish, rm -r) are refused.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| command | Yes | ||
| timeoutSeconds | No |
Changes observed during successful MCP inspections.
v0.4.0Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
While the annotations provide a general destructive hint, the description provides specific operational transparency by listing concrete examples of destructive commands and detailing the OS environment supported, adding significant context beyond the structured hint.
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 highly efficient, front-loading the core function and immediately following up with the most critical operational constraints regarding safety and environment.
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?
Despite the robust safety and operational framing, the tool definition lacks completeness because, given the 0% schema description coverage, it does not explain what `cwd` (Current Working Directory) or `timeoutSeconds` achieve or how they should be used.
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%, meaning the description must explain parameters, but it only mentions the command execution mechanism itself. It fails to define the purpose or use cases for the optional `cwd` or `timeoutSeconds` parameters.
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 identifies the function as running a shell command and specifies the runtime environment differences (PowerShell vs sh), making its purpose highly unambiguous relative to the sibling tools.
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 usage guidelines by explicitly listing several destructive operations (force-push, deleting tags, rm -r) that the agent must refuse to execute, thereby defining clear boundaries for safe use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.