Skip to main content
Glama

stop_backend

Stop the shared ComfyUI backend to free GPU and system memory, refusing while jobs are active unless force is set; manually started instances remain untouched.

Instructions

Stop the shared backend now and free all GPU and system memory it holds.

Refuses while jobs are queued or running (possibly another agent's) unless force=True. An unmanaged ComfyUI (started by hand) is never stopped.

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": "stop_backend"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does substantial work: it discloses the precondition-gated refusal, that the guard may be protecting another agent's work, the forced-override path, and the exception that unmanaged ComfyUI processes are never touched. It stops short of saying what happens to in-flight jobs under force and what the call returns.

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?

Three short sentences: action and effect first, then the guard condition, then the exception case. No filler, and the most important constraint is front-loaded after the action.

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 one-parameter, no-output-schema tool this covers the essentials an agent needs to act safely: side effects, refusal conditions, and the unmanaged-process exception. Only the fate of running jobs under force and the response semantics are left implicit.

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 coverage is 0%, so the description must explain the single parameter — and it does: force=True is framed as the override for the queued/running refusal, which conveys the semantic consequence (likely terminating another agent's jobs), not just the type.

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 ('stop'), a specific resource ('the shared backend'), and the concrete effect (frees all GPU and system memory). An agent can immediately distinguish it from start_backend and from generation siblings without opening a schema.

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?

Gives an explicit when-not condition (refuses while jobs are queued or running — possibly another agent's) and the escape hatch (force=True). It doesn't name an alternative to consult first (e.g. a status tool to verify idle state), which keeps it below 5.

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