Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Set stack policy

stack_set
DestructiveIdempotent

Set per-stack automation on an owned stack: arm or disarm Auto land and pin Vortex auto-review, Cyclone auto-patch, conflict resolution, or CI fixes for that stack only, without changing account settings.

Instructions

Set per-stack automation on one owned Mergestorm stack: auto_land arms or disarms Auto land; auto_review, auto_patch, auto_resolve_conflicts, and auto_fix_ci pin Vortex auto-review, Cyclone auto-patch, Auto-resolve merge conflicts, or Auto-fix failing CI for this stack only (true or false), and null clears the pin so the stack follows the account setting again. Pass at least one key. Never changes account settings. Follow watch.next.args until watch.done; background watching requires a confirmed host notification. See server instructions.

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": {
      "stack_id": "<stack_id>"
    },
    "name": "stack_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
stack_idYes
auto_landNo
auto_patchNo
auto_fix_ciNo
auto_reviewNo
auto_resolve_conflictsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations, the description explains that changes are scoped to one stack, that null clears a pin so the stack follows the account setting again, and that account settings are never changed. These are meaningful behavioral details for a mutation tool. It still does not explain permissions, immediate downstream effects of arming Auto land or auto-patch, or what a successful response looks like.

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 parameter semantics are front-loaded and dense but useful. However, the description is a long run-on sentence, and the trailing instruction to follow watch.next.args and the note about background watching feel tangential to setting stack policy. 'See server instructions' is also vague and adds little standalone value.

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 six-parameter mutation tool with no output schema and no schema descriptions, the description covers the key semantic gaps well: per-stack scope, null-reset behavior, and the at-least-one-key rule. It is somewhat incomplete on permissions, consequence severity, and response behavior, but the annotations already declare destructive, idempotent, and open-world traits.

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

Parameters5/5

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 full burden and does so effectively. It maps every automation parameter to its specific behavior, states the true/false meaning, and explains that null clears the pin for the nullable fields. It also adds the constraint to pass at least one key.

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 states a specific verb and resource: set per-stack automation on one owned Mergestorm stack. It distinguishes this from account-level behavior by saying it applies to this stack only and never changes account settings. The enumerated automation fields make the scope concrete enough for an agent to identify the tool.

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?

It clearly frames usage around per-stack automation and explicitly says not to expect account-level changes. It also states that at least one automation key must be passed, which is important usage guidance. It does not name a specific sibling tool to use for account-level settings, so the alternative routing is implied rather than explicit.

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