Skip to main content
Glama

clawbridge_create_draft_pr

Create a GitHub draft PR after delivery verification to open review-ready changes safely; uses existing CLI auth and never merges or force-pushes.

Instructions

Create a GitHub draft PR after delivery verification. This uses the worker's existing GitHub CLI authentication; it never merges or force-pushes.

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": {
      "taskId": "<taskId>",
      "title": "<title>",
      "body": "<body>"
    },
    "name": "clawbridge_create_draft_pr"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
titleYes
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations supplied, this sentence carries real weight: it discloses that authentication comes from the worker's existing GitHub CLI session (no token plumbing needed) and that the operation is non-destructive with respect to merge/force-push. It does not say what repository or base branch the PR targets, what happens if a PR already exists, or what is returned, so the mutation profile is only partly disclosed.

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?

Two tight sentences, front-loaded with the action and immediately followed by the auth/non-destructive caveat. Nothing is redundant or padded.

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

Completeness3/5

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

For a mutation tool with no annotations, no output schema, and zero parameter documentation, the description covers the two most important behavioral facts (auth source, no merge/force-push). It leaves unresolved which repo/branch is used and what the caller receives back (PR URL/number), which an agent needs to chain this into a workflow.

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

Parameters2/5

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

Schema description coverage is 0% across three parameters, so the description must compensate and it does not — taskId (a UUID) is never explained as the link that determines the target repo/branch, and title/body semantics (length limits, formatting) are untouched. An agent must guess how taskId drives the PR creation.

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?

Names a specific verb and resource ('Create a GitHub draft PR') plus a precondition ('after delivery verification'), which clearly separates it from siblings like clawbridge_verify_delivery or clawbridge_submit. It stops short of naming an alternative tool explicitly, so it lands just below the top mark.

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?

'After delivery verification' gives a concrete prerequisite that implies the ordering with the verification step, and 'never merges or force-pushes' signals the boundary of what this tool is for. There are no explicit exclusions (e.g., non-draft PRs, existing PRs), which keeps it out of 5 territory.

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