Skip to main content
Glama

Start a Workflow run

start_workflow_run
Destructive

Start a run of a Workflow’s current version, which spends credits: start one only when the user agrees. A GitHub Workflow translates its primary branch unless given a watched branch, and delivers by pull request unless delivery: "push". A Workflow reading a Contentful space runs over its whole selection and takes neither argument (refused with VALIDATION_ERROR). Refused with INSUFFICIENT_CREDITS (402) when the organisation is out of credits, and with WORKFLOW_AWAITING_CONVERSION_MERGE (409) while the pull request of the Conversion that created the Workflow is open (only it starts runs until it is merged; the error names it). Returns the run at once; poll get_workflow_run. When referring to a project or language in your reply to the user, use its name and locale (e.g. "French (fr-FR)") — ids (UUIDs) are for tool calls only, never show them to the user.

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": {
      "workflowId": "<workflowId>"
    },
    "name": "start_workflow_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
branchNoGitHub only: a watched branch; the primary (first) one when absent
deliveryNoGitHub only: "pr" (default) or "push" to the branch
workflowIdYesWorkflow id, from list_workflows or set_up_workflow

Output Schema

NameRequiredDescriptionDefault
idYesPass to get_workflow_run
numberYes`run #n`, numbered per Workflow from 1
statusYespending, processing, held (at an approval Gate), completed, failed or superseded. completed means translated, not delivered: read `outputs`
failureYesWhy a failed run failed; null otherwise
outputsYesEach Output of the pinned version and its delivery outcome
triggerYes
createdAtYes
languagesYesOne per target language, once the run has split into languages; empty before
updatedAtYes
runPageUrlYesThe run’s page in the Globalize app
workflowIdYes
versionNumberYesThe Workflow version the run pinned
pullRequestUrlYesThe pull request a GitHub Output opened or updated; null when none

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only flag destructive/openWorld; the description adds the concrete cost model (credit spend), two specific failure modes with status codes (INSUFFICIENT_CREDITS 402, WORKFLOW_AWAITING_CONVERSION_MERGE 409), and the VALIDATION_ERROR case for Contentful-backed workflows. It also clarifies the call is asynchronous and must be polled.

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?

The credit/consent constraint is correctly front-loaded and the sentence order follows the agent's decision path. The final sentence about using names and locales in user-facing replies is a stylistic convention rather than tool behavior, which slightly dilutes focus.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return values are covered by the output schema, and the description still tells the agent the run returns immediately and must be polled. Combined with the error taxonomy and workflow-type branching, an agent has everything needed to call this correctly.

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 100%, so the baseline is 3, but the description earns more by explaining conditional applicability: branch and delivery are GitHub-only and are refused for Contentful-space workflows, and defaults (primary watched branch, pr delivery) are spelled out in prose. It stops short of elaborating each enum value beyond what the schema already says.

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?

"Start a run of a Workflow's current version" gives a specific verb plus resource and bounds it to the current version. It is immediately distinguishable from siblings like get_workflow_run and list_workflow_runs, which read rather than launch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit consent gate ("start one only when the user agrees") is stated before anything else. It also names the follow-up tool ("poll get_workflow_run") and sets out workflow-type-specific conditions that select or forbid the call.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.