Executes short allowlisted, read-only commands without shell syntax to safely inspect files and system diagnostics.
Run a short, read-only allowlisted command without a shell. No arbitrary command or shell syntax is accepted.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | /app | |
| args | No | ||
| timeoutMs | No | ||
| executable | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does disclose the important traits: read-only, allowlisted executable set, no shell interpretation, short-lived. It omits permission requirements, what happens on timeout, and what the response contains, so it is helpful but incomplete for a no-annotation tool.
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 tight sentences, with the safety constraint front-loaded before the exclusion. No filler or redundancy.
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, yet the description gives an agent enough to call the tool safely: the executable set is enumerated in the schema and the shell/allowlist restrictions are stated. The only meaningful gap is the absent explanation of output shape and timeout behavior.
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% across 4 parameters, so the description must compensate. 'Without a shell' usefully clarifies that args are passed as direct argv rather than a command string, but cwd and timeoutMs receive no explanation and the allowlist itself is only visible via the enum.
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 (run) and resource (allowlisted command) with the key constraint that it is short, read-only, and shell-free. This distinguishes it implicitly from siblings like start_process, though no sibling is named explicitly.
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 makes clear that arbitrary commands and shell syntax are rejected, which is a useful guardrail, but it never states when to prefer this over start_process, read_file, or list_directory. Usage is only inferable from the read-only/short framing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.