Skip to main content
Glama
harshmaur

GitLab MCP Server

by harshmaur

create_merge_request_thread

Add discussion threads to GitLab merge requests for code review, feedback, and collaboration on specific changes.

Instructions

Create a new thread on a merge request

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYesProject ID or complete URL-encoded path to project
merge_request_iidYesThe IID of a merge request
bodyYesThe content of the thread
positionNoPosition when creating a diff note
created_atNoDate the thread was created at (ISO 8601 format)

Implementation Reference

  • Zod input schema for creating a new merge request thread/discussion, matching the tool 'create_merge_request_thread' parameters: project_id (inherited), merge_request_iid, body, optional position and created_at.
    export const CreateMergeRequestThreadSchema = ProjectParamsSchema.extend({
      merge_request_iid: z.number().describe("The IID of a merge request"),
      body: z.string().describe("The content of the thread"),
      position: MergeRequestThreadPositionSchema.optional().describe(
        "Position when creating a diff note"
      ),
      created_at: z.string().optional().describe("Date the thread was created at (ISO 8601 format)"),
    });
  • Supporting schema for position parameter in diff notes when creating merge request threads.
    export const MergeRequestThreadPositionSchema = z.object({
      base_sha: z.string().describe("Base commit SHA in the source branch"),
      head_sha: z.string().describe("SHA referencing HEAD of the source branch"),
      start_sha: z.string().describe("SHA referencing the start commit of the source branch"),
      position_type: z.enum(["text", "image", "file"]).describe("Type of position reference"),
      new_path: z.string().optional().describe("File path after change"),
      old_path: z.string().optional().describe("File path before change"),
      new_line: z.number().nullable().optional().describe("Line number after change"),
      old_line: z.number().nullable().optional().describe("Line number before change"),
      width: z.number().optional().describe("Width of the image (for image diffs)"),
      height: z.number().optional().describe("Height of the image (for image diffs)"),
      x: z.number().optional().describe("X coordinate on the image (for image diffs)"),
      y: z.number().optional().describe("Y coordinate on the image (for image diffs)"),
    });
  • Type export for the thread creation options, confirming schema usage in tool definition.
    export type CreateMergeRequestThreadOptions = z.infer<typeof CreateMergeRequestThreadSchema>;
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Create' implies a write/mutation operation, the description doesn't mention authentication requirements, permission levels needed, whether threads are editable/deletable, rate limits, or what happens on success/failure. For a creation tool with complex parameters, this leaves significant behavioral gaps.

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?

The description is a single, efficient sentence that states the core purpose without unnecessary words. It's front-loaded with the essential information and contains zero redundant or verbose elements. For a tool with comprehensive schema documentation, this level of conciseness is appropriate.

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 creation tool with 5 parameters (including a complex nested 'position' object), no annotations, and no output schema, the description is inadequate. It doesn't explain what a 'thread' means in this context (versus a 'note'), doesn't mention the expected response format, and provides no guidance on error conditions or success criteria. The agent would struggle to use this tool effectively without trial and error.

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?

The schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema - it doesn't explain relationships between parameters (like how 'position' relates to 'body'), doesn't provide examples, and doesn't clarify when certain parameters are needed versus optional. This meets the baseline for high schema coverage.

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?

The description clearly states the action ('Create a new thread') and target resource ('on a merge request'), which is specific and unambiguous. However, it doesn't differentiate from similar sibling tools like 'create_merge_request_note' or 'create_issue_note', which might create confusion about when to use this particular thread creation tool versus other note/comment creation tools.

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?

The description provides no guidance on when to use this tool versus alternatives. With multiple sibling tools for creating notes, discussions, and threads (e.g., create_merge_request_note, create_issue_note, list_issue_discussions, mr_discussions), the agent receives no help in selecting this specific thread creation tool over other communication-related tools in the server.

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/harshmaur/gitlab-mcp'

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