Skip to main content
Glama

colab_run_job

Run isolated builds and tests on a shared Colab VM with CPU/GPU/TPU options, workspace sync, artifact collection, and wait or async job modes.

Instructions

Build or test on a shared Colab VM. Defaults to CPU, syncing an absolute local workspace, and waiting up to 300 seconds. Async returns a job ID. cwd and artifactPaths are workspace-relative.

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": "colab_run_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNo
envNo
modeNowait
commandYes
hardwareNocpu
artifactPathsNo
syncWorkspaceNo
workspacePathNo
timeoutSecondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With only openWorldHint=true in the annotations, the description carries the burden and delivers: it discloses default hardware (CPU), default timeout (300s), that a local workspace is synced, and that async mode returns a job ID instead of output. It omits whether syncing overwrites or deletes remote files and how results are returned in wait mode, which are the remaining behavioral gaps.

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?

Four short sentences with the primary purpose front-loaded, followed by defaults, async behavior, and path semantics. Slight ambiguity in 'syncing an absolute local workspace', but there is no filler.

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?

For a 9-parameter tool that runs remote jobs with no output schema and an open-world annotation, the description covers defaults and path conventions but not what a wait-mode call returns (stdout, exit status, artifacts), how workspace sync affects existing remote files, or what env is for. Adequate but incomplete for the complexity.

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

Parameters3/5

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

Schema description coverage is 0% across 9 parameters, so the description must compensate. It adds genuinely useful semantics — cwd and artifactPaths are workspace-relative — and clarifies mode/timeout/hardware behavior, but `env`, `workspacePath` (and its relationship to the 'absolute local workspace'), and `command` itself are left unexplained, so clear gaps remain.

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 states a specific action and target — building or testing on a shared Colab VM — which is clearly distinct from the sibling operations colab_cancel_job, colab_job_status, and colab_pool_* tools. It stops short of saying it executes an arbitrary shell command (the actual `command` parameter), so the verb is slightly softer than the real function.

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 only implied: 'Async returns a job ID' hints that wait mode blocks and async mode pairs with colab_job_status, but the description never states when to choose one over the other or when to prefer a different tool. No prerequisites or exclusions are given.

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