Skip to main content
Glama

hf_runtime_start

Provision a Hugging Face GPU machine with Jupyter for interactive ML work, returning immediately so you can connect once the runtime is ready.

Instructions

Rent a Hugging Face machine running Jupyter, to use like a Colab/Kaggle runtime.

Returns at once; then call hf_runtime_connect (the machine needs a minute or two). Billing runs per minute until hf_runtime_stop, the timeout, or idle_minutes with nothing running — whichever comes first. The disk is temporary: push results with hf_push_run or save_checkpoint before stopping.

flavor: machine type from hf_hardware, e.g. "t4-small", "a10g-small", "l4x1". timeout: hard time limit such as "2h" or "8h". idle_minutes: shut down after this long with no activity and no run in progress (0 disables the idle shutdown). image: Docker image with Python 3; defaults to an official PyTorch + CUDA image.

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": "hf_runtime_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageNo
flavorNocpu-basic
timeoutNo2h
idle_minutesNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: async start with a one-to-two minute readiness delay, per-minute billing that terminates on hf_runtime_stop, timeout, or idle_minutes, and a warning that the disk is temporary and results must be pushed before stopping. These are exactly the behavioral facts an agent needs and cannot get from schema or annotations.

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?

Front-loaded with purpose, then lifecycle, then a per-parameter block. Every sentence conveys actionable information; the only slight redundancy is repeating machine-type framing in both the purpose line and the flavor line.

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?

An output schema exists so return values need no explanation, and the description covers async behavior, cost model, data persistence risk, and all parameters. Complete enough to call correctly; only default values for flavor, timeout, and idle_minutes are left to the schema.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate, and it defines all four parameters: flavor (sourced from hf_hardware with example values), timeout format ('2h', '8h'), idle_minutes including the meaning of 0, and image requiring Python 3 with a stated default. Minor gaps remain, such as not stating the cpu-basic default for flavor or the 2h/30 defaults.

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?

States a specific verb and resource ('Rent a Hugging Face machine running Jupyter') and immediately frames it against familiar analogues (Colab/Kaggle runtime), which distinguishes it from sibling start tools like colab_runtime_start and kaggle_runtime_start without naming them.

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?

Explicitly says the call returns at once and that the agent should then call hf_runtime_connect, and names hf_runtime_stop as the ending action, giving a clear lifecycle. It does not explicitly say when to prefer this over the Colab/Kaggle variants, but the analogy implies it.

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