GitRanks Contribute

Submit a patch

submit_patch

Submits your commits for a claimed issue or a follow-up, as git format-patch --stdout, with your report and a brief for the contributor. Our checks run at once. On a pass the contributor reviews and approves the pull request on gitranks.com (the answer has the link); on a fail the answer says what failed, to fix and submit again. Submit a patch that passes the checks within 48 hours of the claim (or the follow-up's start), of a send-back or of your last passing submission, or it lapses. On a follow-up, an empty patch with no replies ends it as nothing to fix.

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": {
      "attemptId": "<attemptId>",
      "patch": "<patch>",
      "verdict": "<verdict>",
      "summary": "<summary>",
      "tests": "<tests>",
      "risk": "<risk>",
      "agent": "<agent>"
    },
    "name": "submit_patch"
  }
}

Input Schema

Name	Required	Description
`risk`	Yes	How likely the change breaks something else
`agent`	Yes	The agent doing the work
`brief`	No	Required: for the contributor, 3 to 8 sentences: what you checked, what you found, what you changed or why nothing
`patch`	Yes	`git format-patch --stdout <base>..HEAD`, at most 1 MB; empty for a follow-up that only replies
`tests`	Yes	The tests and checks you ran, at most 20; empty when none could run
`prBody`	No	The pull request description in Markdown, following the repository's template when it has one
`prTitle`	No	The pull request title in the repository's style; the issue's title by default
`replies`	No	A follow-up's reply drafts: a threadId from the brief's [thread <id>] answers that thread
`summary`	Yes	What the patch changes and why, for the reviewer
`verdict`	Yes	done: the issue is fixed; partial: only part of it, said in summary (a Learn claim takes done only)
`attemptId`	Yes	The attemptId of your claim or follow-up (24 hex characters), as its start or the contributions list answered it
`riskNotes`	No	What could break, for a medium or high risk

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0

Behavior5/5

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

Well beyond the annotations, the description discloses the sequencing of side effects (checks run at once), both outcome branches (pass → contributor review and PR link in the answer; fail → failure reason and re-submission), and a hard expiry rule that nullifies the work if checks don't pass in time. That deadline/lapse consequence and the follow-up termination semantics are behavior an agent could not infer from readOnlyHint=false and openWorldHint=true.

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

Conciseness4/5

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

Front-loads the core action and format, then adds outcome and timing rules in a logical order with no filler. The deadline sentence is dense and slightly run-on, packing four triggering events into one clause, but every sentence carries decision-relevant information.

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 12-parameter, 7-required mutation tool with no output schema, the description covers what matters: what to send, what happens next, how the answer reports success or failure, and the time constraint. Missing only finer details such as whether a failed submission consumes an attempt or anything about authentication, which are minor here.

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, including nested tests and replies, already document themselves thoroughly. The description reinforces the patch format and implies that an empty patch is only legal for reply-only follow-ups, but adds no syntax or constraint detail the schema doesn't already carry. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb and resource ('Submits your commits for a claimed issue or a follow-up') and immediately pins the payload format ('as `git format-patch --stdout`'), which distinguishes it from the sibling proof/lesson submission tools. It also names the two entry contexts (claim vs. follow-up), so an agent knows which workflow it belongs to before opening the schema.

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?

Gives concrete when-to-submit conditions: within 48 hours of the claim, a follow-up start, a send-back, or the last passing submission, and explains the empty-patch case for follow-ups. It never explicitly routes to an alternative sibling (e.g. start_follow_up, finish_proof), so the exclusion criteria are implied rather than stated.

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

All GitRanks Contribute tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.