Skip to main content
Glama

get_vram_usage

Monitor live GPU memory and utilization directly from the driver to avoid torch reporting zero when ComfyUI holds CUDA tensors.

Instructions

Monitor live GPU memory and utilisation.

Reads the driver, not torch: this process holds no CUDA tensors, so torch would report 0 no matter what ComfyUI is actually holding.

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": "get_vram_usage"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose a meaningful behavioral trait beyond the name: the measurement comes from the driver, and a torch-based reading would return 0 because the process holds no CUDA tensors. That prevents a serious misinterpretation of results. It stops short of 5 because it does not say whether the reading is an instantaneous snapshot or a sampled/windowed value.

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 the core purpose in the first sentence, followed by a short justification for the non-obvious data source. The second sentence is a two-line aside that is somewhat explanatory rather than operational, but it earns its place by preventing a wrong comparison against torch-reported numbers.

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?

Low-complexity, zero-parameter tool with an output schema, so return values need not be explained. The description covers what is read and where it comes from. The remaining gaps (snapshot vs. sampled reading, relationship to system_check) are minor but real for a monitoring tool.

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 nothing for the description to disambiguate; baseline is 4. The description correctly adds no parameter noise.

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?

States a specific verb and resource: 'Monitor live GPU memory and utilisation.' An agent immediately knows this reads GPU VRAM/utilisation, and the second sentence clarifies the data source (driver rather than torch). It does not explicitly distinguish itself from plausible siblings such as system_check or get_comfyui_status, which may also surface hardware metrics, so it stops short of a 5.

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?

There is no explicit when-to-use/when-not statement or sibling routing. The 'reads the driver, not torch' note implicitly tells the agent why a torch-based reading would be wrong and therefore why this tool exists, which is useful contextual guidance, but the agent must infer when to prefer this over system_check.

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