Skip to main content
Glama

Open a pull request

open_pr

Through the Shipfound GitHub App, when the founder connected GitHub for this product: a new branch named shipfound/ off the default branch, one commit with the files given (each file's whole new content, or delete), and a pull request for the founder to review and merge. Never merges, never pushes to an existing branch, never touches .github/, env files, keys or secrets; at most 20 files, one theme per PR. Then record_action it (kind PR, url = the PR) and verify. For an agent without the code; in Claude Code or Codex use git and gh. Free.

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": {
      "title": "<title>",
      "branch": "<branch>",
      "files": "<files>"
    },
    "name": "open_pr"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoWhat it changes and why, for the founder reviewing it.
filesYesEach file to write (path and whole content) or delete (path, delete: true).
titleYesThe pull request's title: what it changes for the visitor, in a few words.
branchYesA new branch, shipfound/<short-slug>, like shipfound/home-headline.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses hard boundaries that materially change planning: no touching .github/, env files, keys or secrets, at most 20 files, one theme per PR, and no pushes to existing branches. It also notes the output is a PR for human review and that the tool is free, which the annotations do not convey.

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 core purpose is front-loaded, but the whole entry is a single run-on, elliptical sentence with fragmentary clauses and a dangling 'Free.' Every fact is useful, yet several restate schema constraints (20 files, whole content) and the grammar makes it slower to parse than it needs to be.

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

Completeness4/5

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

For a mutating, open-world tool with no output schema, the definition covers inputs, constraints, prerequisite auth, and the post-call workflow, which is substantial. It leaves unstated what the response contains and what happens on failure (e.g. duplicate branch name or denied permission), though 'url = the PR' implies a url field is returned.

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%, and nearly every hint in the description (whole-file content or delete, shipfound/<slug> branch naming, 20-file cap) is already carried by the schema's property descriptions and maxItems. The description adds emphasis and the 'one theme per PR' convention, but no format or syntax the schema lacks, so baseline 3 applies.

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 names the exact mechanics: a new branch shipfound/<slug> off the default branch, one commit with the supplied files (full content or delete), and a PR for the founder to review and merge. It also states plainly what it never does (never merges, never pushes to an existing branch), so an agent can distinguish this from a generic git/gh workflow.

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?

It gives the precondition (founder has connected GitHub for this product) and an explicit alternative path: an agent without the code should use git and gh inside Claude Code or Codex. It also chains the required follow-up calls, 'record_action it (kind PR, url = the PR) and verify', so the agent knows this is not a terminal step.

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.

Resources