Skip to main content
Glama

kaggle_runtime_start

Starts a Kaggle GPU or CPU session headlessly using your Kaggle login, optionally attaching competition data or datasets, so you can then connect and run training tools on the Kaggle machine.

Instructions

Start a Kaggle GPU session without the browser, using the user's Kaggle login.

Returns at once; then call connect_runtime (Kaggle needs a minute or two). After that every runtime tool works on the Kaggle machine. It uses the account's free weekly GPU hours until runtime_stop, max_hours, or idle_minutes with nothing running.

competition: a competition slug to attach; its data appears under /kaggle/input/. (The user must have accepted the competition rules on kaggle.com.) datasets: comma-separated "owner/dataset" names to attach under /kaggle/input/. gpu: False starts a CPU session, which does not use GPU quota.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "kaggle_runtime_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
gpuNo
datasetsNo
max_hoursNo
competitionNo
idle_minutesNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and discloses key traits: it requires the user's Kaggle login, returns immediately, consumes free weekly GPU hours, and stops via runtime_stop, max_hours, or idle_minutes. It also notes that competition rules must be accepted. Failure modes and behavior when a session already exists are not covered.

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

Conciseness5/5

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

The description is front-loaded with the core action and immediate-return caveat, then lists parameter details compactly. Every sentence adds practical value and the structure matches the call sequence an agent needs.

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

Completeness4/5

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

For a five-parameter start tool with no annotations and an existing output schema, the description covers authentication, quota use, stop conditions, and the three most operationally distinct parameters. The main gap is fuller semantics for max_hours and idle_minutes, plus error or already-running behavior.

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%, so the description must explain all five parameters. It meaningfully describes competition, datasets, and gpu, including where attached data appears under /kaggle/input/. However, max_hours and idle_minutes are only mentioned as stop conditions without explaining their defaults, units, or interaction in detail.

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

Purpose5/5

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

The description states a specific verb and resource: 'Start a Kaggle GPU session without the browser'. It also distinguishes the immediate-return behavior from connect_runtime, making the lifecycle role clear to an agent.

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

Usage Guidelines4/5

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

It gives clear sequencing guidance: call this first, then connect_runtime after a minute or two. It also explains that gpu=False starts a CPU session without GPU quota. It does not explicitly say what to do if a session is already running or when to prefer a different runtime backend, but the Kaggle-specific context is clear.

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