Skip to main content
Glama
Tiberriver256

Azure DevOps MCP Server

create_work_item

Create Azure DevOps work items like bugs, tasks, or user stories by providing type, title, and optional fields for assignment, priority, tags, area, iteration, and parent.

Instructions

Create a new work item

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoTags to add to the work item
titleYesThe title of the work item
areaPathNoThe area path for the work item
parentIdNoThe ID of the parent work item to create a relationship with
priorityNoThe priority of the work item
projectIdNoThe ID or name of the project (Default: MyProject)
assignedToNoThe email or name of the user to assign the work item to
descriptionNoWork item description in HTML format. Multi-line text fields (i.e., System.History, AcceptanceCriteria, etc.) must use HTML format. Do not use CDATA tags.
workItemTypeYesThe type of work item to create (e.g., "Task", "Bug", "User Story")
iterationPathNoThe iteration path for the work item
organizationIdNoThe ID or name of the organization (Default: mycompany)
additionalFieldsNoAdditional Azure DevOps fields to set by reference name (fields not exposed as named parameters). Example for Bug severity: { "Microsoft.VSTS.Common.Severity": "1 - Critical" } (accepted values: "1 - Critical", "2 - High", "3 - Medium", "4 - Low"). Multi-line text fields (i.e., System.History, AcceptanceCriteria, etc.) must use HTML format. Do not use CDATA tags.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.6
    • changedInput schema / properties / additionalFields / description
      Previous value: -"Additional fields to set on the work item. Multi-line text fields (i.e., System.History, AcceptanceCriteria, etc.) must use HTML format. Do not use CDATA tags."New value: +"Additional Azure DevOps fields to set by reference name (fields not exposed as named parameters). Example for Bug severity: { \"Microsoft.VSTS.Common.Severity\": \"1 - Critical\" } (accepted values: \"1 - Critical\", \"2 - High\", \"3 - Medium\", \"4 - Low\"). Multi-line text fields (i.e., System.History, AcceptanceCriteria, etc.) must use HTML format. Do not use CDATA tags."
    • addedInput schema / properties / additionalFields / propertyNames
      Added value: +{
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / tags
      Added value: +{
      +  "description": "Tags to add to the work item",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  3. Changed5 schema fields changedv1.0.0
    • changedInput schema / properties / additionalFields / description
      Previous value: -"Additional fields to set on the work item"New value: +"Additional fields to set on the work item. Multi-line text fields (i.e., System.History, AcceptanceCriteria, etc.) must use HTML format. Do not use CDATA tags."
    • changedInput schema / properties / description / description
      Previous value: -"The description of the work item"New value: +"Work item description in HTML format. Multi-line text fields (i.e., System.History, AcceptanceCriteria, etc.) must use HTML format. Do not use CDATA tags."
    • addedInput schema / properties / organizationId
      Added value: +{
      +  "description": "The ID or name of the organization (Default: mycompany)",
      +  "type": "string"
      +}
    • changedInput schema / properties / projectId / description
      Previous value: -"The ID or name of the project"New value: +"The ID or name of the project (Default: MyProject)"
    • changedInput schema / required
      Previous value: -[
      -  "projectId",
      -  "workItemType",
      -  "title"
      -]New value: +[
      +  "workItemType",
      +  "title"
      +]
  4. First observed

TDQS

C2.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries the entire behavioral burden, and it discloses nothing about permissions required, whether the operation is reversible, what relationships (e.g. parentId linking) are set up, or what is returned. The use of 'Create' at least signals a mutation, but no substantive behavioral context is offered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is front-loaded and free of padding, but its brevity reflects under-specification rather than disciplined conciseness. It does not earn its place as a full description of a 12-parameter mutation tool.

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

Completeness2/5

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

For a 12-parameter mutation tool with no annotations and no output schema, the description is far too thin. The rich schema mitigates the parameter gap (100% coverage), but nothing addresses permissions, project defaults, relationship side effects, or post-creation behavior.

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%, so all 12 parameters are already documented in the schema, including the non-obvious additionalFields HTML-formatting notes and defaults. The description adds nothing beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The phrase 'Create a new work item' names a clear verb and resource, but it essentially restates the tool name create_work_item and adds no scope, differentiation, or detail about what a work item is. Siblings like update_work_item and get_work_item are distinguished only by the verb, with no explicit contrast drawn in the description.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus update_work_item, get_work_item, or list_work_items, nor any prerequisites such as required project/organization context. The agent must infer everything about invocation context.

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