Skip to main content
Glama

run_workflow

Runs a named ComfyUI workflow with custom inputs, validates it before execution, and returns a job ID for tracking generated files.

Instructions

Runs one of your workflows. inputs = {"prompt": "...", "image": "C:/pics/cat.png", "steps": 20} using the names from list_workflows; a file path for image/video/audio is copied into ComfyUI for you. A new random seed each run unless you pass seed or keep_seed=true. Checks the workflow first and refuses if it would fail (force=true runs anyway). Returns a job id: wait with job_status; the saved files come back in "files".

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "run_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
forceNo
inputsNo
priorityNouser
keep_seedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

Adds substantial behavior beyond the annotations: fresh random seed per run unless seed/keep_seed=true, a pre-flight check that refuses execution, force to bypass it, and an async job-id return with files delivered later. That is real disclosure the annotations don't carry. It loses a point because it never says what running a workflow produces/overwrites on disk or what permissions/GPU state it requires, which matters for a non-read-only, closed-world job submitter.

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 action, then each sentence adds a distinct operational fact (inputs format, seeding, validation gate, job-id return). The inline JSON example is valuable but is wedged mid-sentence, making the first paragraph harder to parse than necessary; trimming the repeated file-type list would help.

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?

With no output schema and no per-parameter schema descriptions, the description steps up: it explains the nested `inputs` object, the seed default, the refusal behavior, and the return contract (job id + files). Only `priority` and the placement of `seed` are left unexplained, which keeps it from a 5.

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 compensate, and it largely does: it shows the `inputs` object shape with a concrete JSON example, notes that image/video/audio paths are copied into ComfyUI automatically, and explains `keep_seed` and `force`. The `priority` parameter is never mentioned anywhere and `seed` is referenced without being tied to a schema field, leaving a real gap.

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?

Opens with a specific verb+resource ("Runs one of your workflows") and immediately grounds the `name` parameter in the sibling tool `list_workflows`, which separates it from check_workflow/save_workflow. It stops short of an explicit contrast statement, but the purpose is unambiguous.

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 concrete routing: get names from list_workflows, expect a validation pass that refuses on failure, override with force=true, then wait with job_status. It covers the when/how chain well but never states when NOT to use it (e.g., use check_workflow first to preview, or estimate for cost).

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