Frees GPU VRAM by terminating all compute processes. Use when ComfyUI runs out of memory.
Kill ALL GPU compute processes and free VRAM. Use with caution.
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": "vram_flush"
}
}| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden for behavioral traits. It clearly states a destructive action: killing all compute processes and freeing VRAM. The warning adds a cautionary note. However, it does not detail required permissions, reversibility, or impact on running jobs, which would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two short sentences. The first sentence states the action, the second adds a necessary warning. Every word earns its place with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no parameters and no output schema, the description adequately covers the essential information. It tells the agent what the tool does and includes a caution. However, additional context about when to use it or potential side effects would make it more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters and schema coverage is 100%, so the description's job is to explain the tool's effect. It does so effectively by describing the action in plain language. No additional parameter meaning is needed, but the description does not add extra context beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb-resource pair ('Kill ALL GPU compute processes and free VRAM') that clearly states the tool's action and scope. It distinguishes from siblings like gpu_flush_models or gpu_processes by indicating it kills all processes, not just a subset.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes 'Use with caution' as a warning but provides no explicit context on when to use this tool versus alternatives like gpu_flush_models or gpu_auto_manage. It does not mention prerequisites, safety considerations, or situations where this tool is appropriate versus inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.