Skip to main content
Glama
computercraft-mcp
by slashracer5

cc_shell

Run a shell command or program in an in-game ComputerCraft computer and return its output, with errors and printError text reported in stderr. Use it to check files (ls) or execute programs with arguments.

Instructions

Run a shell command or program (ls, edit-less programs, myprogram arg) and return its output.

A failing program returns ERROR with the message and its printError output in stderr. Interactive programs that wait for keys will time out.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "command": "<command>"
    },
    "name": "cc_shell"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYes
timeoutNo
computerNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true. On top of that the description adds real behavioral detail the annotations cannot convey: failures surface an ERROR message with printError output in `stderr`, and interactive programs time out rather than hanging forever. It stops short of stating which environment the command runs in or what permissions are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with the core action front-loaded and the failure/interactive caveats following in priority order. Nothing is wasted, though the parenthetical example list is slightly noisy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because an output schema exists, the description is not obliged to spell out return values, and its stderr note is a bonus. However, a command-execution tool with an unexplained `computer` selector and an unexplained timeout leaves material gaps about where the command executes and how long it is allowed to run.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters, so the description carries the full burden and largely fails it. It never explains `timeout` (default 30 seconds, unit and behavior on expiry) or `computer` (an optional integer selecting a target machine), which are exactly the parameters an agent is most likely to misuse.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource: run a shell command or program and return its output, with concrete examples (`ls`, `myprogram arg`). It is clearly a command-execution tool, but it never distinguishes itself from sibling execution tools such as cc_exec or cc_call, which an agent would need to choose correctly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the agent is expected to reach for this whenever it wants to execute something, and one exclusion is given (interactive programs that wait for keys will time out). There is no explicit guidance on when to prefer cc_exec, cc_batch, or cc_call, so the choice between siblings is left to inference.

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