Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Restack stack

stack_restack
Destructive

Rebase and push an owned stack's layer branches onto their parents after the trunk or a lower layer moves; does not merge or enqueue anything.

Instructions

Rebase one owned stack's layer branches onto their parents and push them, after the trunk or a lower layer moved. Does not merge or enqueue anything. 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_restack"
  }
}

Input Schema

NameRequiredDescriptionDefault
stack_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructive/openWorld/non-idempotent, and the description layers on real value beyond that: it discloses that branches are pushed to the remote, that nothing is merged or enqueued, and that the call is followed by an async watch loop (watch.next.args until watch.done) that needs a confirmed host notification for background mode. That is meaningful behavioral context, though the pointer to 'server instructions' leaves the watch contract partly off-tool.

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?

Four short sentences, front-loaded with what the tool does and immediately followed by the exclusion and the async follow-up. Only 'See server instructions' is low-value padding since it defers rather than informs.

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?

There is no output schema, and the description supplies the essential post-call protocol (follow watch.next.args until watch.done) plus the notification prerequisite, which is the main thing an agent could get wrong. The remaining gap is identifying a valid stack_id and what done returns.

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 0% for the single stack_id parameter, so the description must carry the load. 'One owned stack' does add the ownership constraint, but no format, source, or example for the identifier is given, so an agent still has to guess where to obtain a valid stack_id.

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?

Names a specific verb (rebase), a specific resource (one owned stack's layer branches), and the accompanying push, with the trigger condition ('after the trunk or a lower layer moved') stated up front. It also explicitly distinguishes itself from stack_enqueue by declaring it 'does not merge or enqueue anything.'

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?

The trigger situation is explicit — call this after the trunk or a lower layer moved — and the negative case (no merge, no enqueue) is stated. It stops short of naming which sibling to use for the merging/enqueueing path, so routing across stack_enqueue/stack_publish is left partly to inference.

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