Skip to main content
Glama
mondaycom

monday MCP Server

Official
by mondaycom

Update Workflow

update_workflow

Update a workflow draft by describing changes in plain English; the AI agent applies structural modifications and returns a summary.

Instructions

Updates an existing workflow draft using an AI agent.

The agent interprets the prompt and applies structural changes to the workflow — creating, updating, or deleting steps. Pass clear, descriptive instructions and the agent will decide which operations to perform, then return a summary of what it did.

Use this after create_workflow to build out the workflow step by step. You can call it multiple times on the same draft to iteratively refine the workflow.

Parameters:

  • workflowObjectId and workflowDraftId: both returned by create_workflow — they identify which draft to update.

  • prompt: describe what you want to change in plain English (e.g. "Add a trigger that fires when an item is created on the Marketing board"). Maximum 2000 characters.

Returns:

  • workflowObjectId: the workflow object ID (unchanged)

  • workflowDraftId: the draft version ID (unchanged)

  • result: agent response describing the changes made

Note: if directing the user to the workflow in the UI, the correct URL path is custom_objects/, not workflows/ — e.g. {account}.monday.com/custom_objects/{workflowObjectId}.

Note: the workflow runs only after it is published to live version.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workflowObjectIdYesThe workflow object ID returned by create_workflow. Identifies the workflow across all its drafts and published versions. Does not change across publishes.
workflowDraftIdYesThe draft version ID to update. Use the workflowDraftId from the previous create_workflow or update_workflow response — the agent may return a new draft ID, so always read it from the latest response rather than reusing an earlier value.
promptYesNatural-language description of the changes to make. Describe what steps to add, remove, or modify in plain English (e.g. "Add a trigger that fires when an item is created on the Marketing board"). The agent interprets this and applies the right structural changes. Maximum 2000 characters.
Behavior5/5

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

The description details that the AI agent interprets the prompt and applies structural changes (creating, updating, deleting steps), returns a summary, and notes that the workflow runs only after publishing. It also includes a UI URL note, adding value beyond annotations.

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 description is well-structured with clear sections (Parameters, Returns, Notes). It is somewhat long but front-loads purpose and usage. Could be slightly more concise but still effective.

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?

Given the complexity of 3 required parameters, no output schema, and no nested objects, the description is thorough. It covers behavior, parameters, returns, and even UI navigation, making it complete.

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

Parameters5/5

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

Schema coverage is 100%, and the description adds context: workflowObjectId and workflowDraftId come from create_workflow, workflowDraftId might change with each update, and prompt includes an example and max length. This adds meaning 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?

The description clearly states it updates an existing workflow draft using an AI agent, specifying the verb 'updates', the resource 'workflow draft', and distinguishes from siblings like create_workflow and publish_workflow.

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?

The description explicitly says 'Use this after create_workflow to build out the workflow step by step' and notes it can be called multiple times. It does not explicitly mention when not to use it, but the context with siblings is clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mondaycom/mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server