Skip to main content
Glama
plunger

plunger

Official

run_workflow

Executes a saved workflow by sending its requests in order, passing values between steps and stopping at the first failure; returns each step's status, set variables, and final response.

Instructions

Run a saved workflow: its requests are sent in order, values are carried from one response to the next (never shown if secret), and it stops at the first step that fails. Returns each step's status and the variables it set, plus the last response in full.

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
nameYesThe workflow's name (see list_workflows).
cleanupNoRemove the variables this run stored once it is done (the later steps have used them by then), so runs do not leave values behind. Values extracted with `scope: "run"` are never stored at all.
variablesNo{{variable}} values for every step of this run.
include_last_responseNoWhether the result carries the last step's full response. Default: yes, unless a `return` produced the output (then it is left out, since the output is the answer). `true` or `false` overrides. The step results, the variables set and the `return` output are always there.

Output Schema

NameRequiredDescriptionDefault
okYesTrue when every step passed.
stepsYes
outputNoWhat the last `return` step produced (see `Step::return`): the answer the run was written to give.
workflowYes
cancelledNoTrue when the run was cancelled before it finished.
steps_runYesHow many steps ran (a failed step stops the rest).
cleaned_upNoWith `cleanup`: the variables the run stored and then removed.
last_responseNoThe last response that came back, in full.
stopped_earlyNoTrue when a `stop_if` ended the run before the last step.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.1
    • addedInput schema / properties / include_last_response
      Added value: +{
      +  "default": null,
      +  "description": "Whether the result carries the last step's full response. Default: yes, unless a `return` produced the\noutput (then it is left out, since the output is the answer). `true` or `false` overrides. The step results,\nthe variables set and the `return` output are always there.",
      +  "type": [
      +    "boolean",
      +    "null"
      +  ]
      +}
    • addedOutput schema / $defs / AgentResponse / properties / error_body
      Added value: +{
      +  "description": "The first few hundred characters of the body of a 4xx or 5xx answer, when `select` left the body out:\nthe reason is usually in it (\"body is not JSON\" tells nothing, the 17 bytes it was do).",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Changed5 schema fields changedv0.8.0
    • addedOutput schema / $defs / AssertOutcome
      Added value: +{
      +  "description": "What one assert found.",
      +  "properties": {
      +    "message": {
      +      "description": "Why it failed.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "ok": {
      +      "type": "boolean"
      +    }
      +  },
      +  "required": [
      +    "name",
      +    "ok"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / $defs / StepResult / properties / asserts
      Added value: +{
      +  "description": "What each of the step's `asserts` found.",
      +  "items": {
      +    "$ref": "#/$defs/AssertOutcome"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / $defs / StepResult / properties / requests
      Added value: +{
      +  "description": "How many requests the step sent (pages, elements, polling attempts and retries each count). Shown when it is not 1.",
      +  "format": "uint",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / $defs / StepResult / properties / warning
      Added value: +{
      +  "description": "Something that did not fail the step but should be known: paging stopped at `max_pages`, some elements failed.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / output
      Added value: +{
      +  "description": "What the last `return` step produced (see `Step::return`): the answer the run was written to give."
      +}
  3. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

With only openWorldHint=true available in annotations, the description carries the burden and does so well: sequential execution, value propagation between steps, secret values never exposed, fail-fast on the first failing step, and what the result contains. These are exactly the traits an agent needs before triggering a multi-step side-effecting run.

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?

Two tight sentences: execution semantics first, result shape second. Every clause earns its place — the secret-handling and fail-fast notes are non-obvious and load-bearing, not filler.

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?

An output schema exists, so return values need only light coverage, and the failure/cleanup semantics are well handled. The one gap is that openWorldHint=true implies real outbound requests with external side effects, which the description never mentions — an agent may not realize this run touches live systems.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each parameter (name, cleanup, variables, include_last_response) is thoroughly documented in-schema, so the baseline of 3 applies. The description's phrase 'the last response in full' loosely echoes include_last_response but adds no syntax or format detail beyond the schema.

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 ('Run a saved workflow') and immediately characterizes it as an ordered multi-step execution, which separates it from single-request siblings like send_request and from save_workflow. An agent knows exactly what this does without opening the schema.

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?

Usage is implied by the tool's nature, and the schema's 'name' description routes discovery to list_workflows, but the description never states when to choose this over send_request or when a workflow run is inappropriate. No exclusions or prerequisites are given.

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