Skip to main content
Glama

free_vram

Asks ComfyUI to unload loaded models and release VRAM while keeping the service running, so you can play games or start other GPU-heavy tasks.

Instructions

让 ComfyUI 卸载模型并释放显存(服务继续运行)。玩游戏或跑别的显卡任务前调用。Ask ComfyUI to unload models and free VRAM while the service keeps running; call it before gaming or another GPU-heavy task.

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": "free_vram"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.2

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does add valuable context by clarifying that the service continues running and that existing models are unloaded, but it does not say whether the call can be made while a generation is in flight, whether loaded models are lost permanently, whether it blocks until VRAM is actually released, or what is reported back on success or failure.

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

Conciseness3/5

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

The action and the usage trigger are front-loaded, which is good, but the entire content is then repeated verbatim in a second language, roughly doubling length without adding information. Trimming to one language, or condensing the duplicate, would make it tighter.

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 zero-parameter, side-effecting utility with no output schema, the description covers the essential facts: what it does, when to call it, and that the server survives. The main omission is return-value or failure behavior, which matters given there is no output schema to fall back on.

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?

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly implies a no-argument operation by describing a single unconditional action.

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: unload models and free VRAM, with the crucial qualifier that the ComfyUI service keeps running. That qualifier alone distinguishes it from a shutdown/restart operation and from the generation-oriented siblings generate, get_result and status.

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

Usage Guidelines5/5

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

Gives an explicit trigger condition in both languages: call it before gaming or another GPU-heavy task. There is no ambiguity about when to reach for this tool rather than generate or status, and no exclusion is needed because the siblings serve unrelated purposes.

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

Deploy Server

Other Tools