Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Start Cyclone job

cyclone_start
Destructive

Starts Cyclone work on a repository to fix open findings or failing CI, resolve pull-request conflicts, or build a new project and open a PR; returns a dispatch ID for monitoring.

Instructions

Have Cyclone work on the user's repository and push the result. task fix_findings fixes the open Vortex findings on pr_number, fix_ci fixes its failing CI check (failing_check names one; default the first failing check), resolve_conflicts merges its base in and resolves the conflicts; each pushes a commit to the pull request's branch. When the user has not named the pull request, find it before you call, and ask them for owner/repo#number if you cannot. task build builds a first working version of a new project from brief into an empty repository the user created and installed Cyclone on, then opens a pull request. Uses Cyclone credits. When the pull request has nothing to do (CI green, no conflicts, no open findings) nothing starts and the answer says why: tell the user that. Returns dispatch_id. Wait for the job with cyclone_job until it is pushed, completed or failed, then report what it pushed. When the result names a background task, its result also arrives through that task when the work finishes.

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": {
      "task": "<task>",
      "owner": "<owner>",
      "repo": "<repo>"
    },
    "name": "cyclone_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
repoYes
taskYes
briefNo
ownerYes
pr_numberNo
failing_checkNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true, openWorldHint=true, and non-idempotency; the description adds the concrete consequences the annotations cannot: commits get pushed to the PR branch, Cyclone credits are consumed, a dispatch_id is returned rather than a result, and the no-work case silently starts nothing. It also discloses that background-task results arrive later through the named task. No contradiction with the annotations.

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?

Dense but content-bearing, with no filler sentences; every clause adds an operational rule. The tradeoff is a long semicolon-chained paragraph rather than front-loaded structure, so the task definitions are harder to scan than they need 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 destructive, open-world mutation with no output schema, the description covers the essentials: it states the return value (dispatch_id), the required follow-up (wait with cyclone_job until pushed/completed/failed), and the credit cost. Minor gaps remain on per-task parameter requirements and roughly how many credits a run consumes.

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

Parameters4/5

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

Schema description coverage is 0%, so the description carries the burden, and it does so for most parameters: task's four values are defined with their operational meaning, pr_number is tied to fix_findings/fix_ci/resolve_conflicts, failing_check has a documented default ('default the first failing check'), and owner/repo is expressed as owner/repo#number. It does not state which parameters are required per task (e.g., whether brief is mandatory for build or pr_number for build is invalid), leaving the enum/parameter interaction partly inferred.

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 gives a concrete verb+resource ('Have Cyclone work on the user's repository and push the result') and then disambiguates all four enum tasks with specific behavior: fix_findings fixes open Vortex findings on pr_number, fix_ci fixes a failing check, resolve_conflicts merges the base and resolves conflicts, build creates a first working version in an empty repo. An agent can select the right task value without 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit prerequisites and preconditions: find the pull request before calling when the user hasn't named it, and ask for owner/repo#number if you cannot. It also names the no-op case ('when the pull request has nothing to do ... nothing starts and the answer says why: tell the user that') and routes the agent to the sibling cyclone_job for waiting.

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