Skip to main content
Glama

create_pull_request

Create a pull request to merge code changes from one branch to another in a GitHub repository.

Instructions

Create a new pull request in a GitHub repository

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ownerYesRepository owner (username or organization)
repoYesRepository name
titleYesPull request title
bodyNoPull request body/description
headYesThe name of the branch where your changes are implemented
baseYesThe name of the branch you want the changes pulled into
draftNoWhether to create the pull request as a draft
maintainer_can_modifyNoWhether maintainers can modify the pull request

Implementation Reference

  • The core handler function that executes the create_pull_request tool logic by parsing inputs, making a POST request to GitHub's /pulls endpoint, and parsing the response.
    export async function createPullRequest(
      github_pat: string,
      params: z.infer<typeof CreatePullRequestSchema>
    ): Promise<z.infer<typeof GitHubPullRequestSchema>> {
      const { owner, repo, ...options } = CreatePullRequestSchema.parse(params);
    
      const response = await githubRequest(
        github_pat,
        `https://api.github.com/repos/${owner}/${repo}/pulls`,
        {
          method: "POST",
          body: options,
        }
      );
    
      return GitHubPullRequestSchema.parse(response);
    }
  • The top-level dispatcher handler in the MCP server that handles the create_pull_request tool call, parses arguments with PAT, delegates to pulls.createPullRequest, and formats the response.
    case "create_pull_request": {
      const argsWithPat = pulls._CreatePullRequestSchema.parse(params.arguments);
      const { github_pat, ...args } = argsWithPat;
      const pullRequest = await pulls.createPullRequest(github_pat, args);
      return {
        content: [{ type: "text", text: JSON.stringify(pullRequest, null, 2) }],
      };
    }
  • Zod schemas defining the input parameters for create_pull_request: CreatePullRequestSchema (public inputs) and _CreatePullRequestSchema (with github_pat for internal use).
    export const CreatePullRequestSchema = z.object({
      owner: z.string().describe("Repository owner (username or organization)"),
      repo: z.string().describe("Repository name"),
      title: z.string().describe("Pull request title"),
      body: z.string().optional().describe("Pull request body/description"),
      head: z.string().describe("The name of the branch where your changes are implemented"),
      base: z.string().describe("The name of the branch you want the changes pulled into"),
      draft: z.boolean().optional().describe("Whether to create the pull request as a draft"),
      maintainer_can_modify: z.boolean().optional().describe("Whether maintainers can modify the pull request")
    });
    
    export const _CreatePullRequestSchema = CreatePullRequestSchema.extend({
      github_pat: z.string().describe("GitHub Personal Access Token"),
    });
  • src/index.ts:108-112 (registration)
    Tool registration in the MCP server's listTools response, specifying name, description, and input schema.
    {
      name: "create_pull_request",
      description: "Create a new pull request in a GitHub repository",
      inputSchema: zodToJsonSchema(pulls.CreatePullRequestSchema),
    },
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It states the tool creates a pull request, implying a write operation, but doesn't cover permissions needed, whether it's idempotent, rate limits, error conditions, or what happens on success (e.g., returns a PR object). For a mutation tool with zero annotation coverage, this is insufficient.

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 action and resource, making it immediately scannable and appropriately sized for its limited content.

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 complex mutation tool with 8 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain the GitHub-specific context (e.g., PR lifecycle), what the tool returns, error handling, or how it fits with sibling tools. The agent would need to infer much from the parameter schema alone.

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 description adds no parameter information beyond what's already in the schema, which has 100% coverage with clear descriptions for all 8 parameters. The baseline score of 3 reflects that the schema adequately documents parameters, so the description doesn't need to compensate, but it also adds no extra value about parameter relationships or usage context.

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 pull request') and resource ('in a GitHub repository'), making the purpose immediately understandable. However, it doesn't differentiate this tool from sibling tools like 'create_issue' or 'create_branch' beyond the obvious resource difference, missing an opportunity to clarify its specific role in the GitHub workflow.

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. It doesn't mention prerequisites (e.g., needing existing branches), when not to use it (e.g., for direct commits), or how it relates to sibling tools like 'submit_pull_request_review' or 'create_issue'. This leaves the agent without contextual usage information.

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/MissionSquad/mcp-github'

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