Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Send stack to merge queue

stack_enqueue
DestructiveIdempotent

Queues an owned stack for testing and automatic landing once its checks pass.

Instructions

Send one owned stack to the Mergestorm merge queue, which tests it and lands it when its checks pass. To restart a failed or stuck land, call stack_restack first and then this. When the result names a background task, its result also arrives through that task when the work finishes. 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_enqueue"
  }
}

Input Schema

NameRequiredDescriptionDefault
stack_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare a destructive, open-world, idempotent write; the description adds real context beyond them: the queue tests before landing, results may be delivered as a background task, and the caller must follow watch.next.args until watch.done with a confirmed host notification. It does not explain why the call is flagged destructive or what idempotency means here (e.g. re-enqueueing an already-queued stack), which is the main remaining gap.

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?

Purpose and outcome are front-loaded, followed by the restart alternative, then the async result and watch-loop mechanics. Each sentence carries distinct operational information with no repetition, and the closing pointer to server instructions is appropriately brief.

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 single-parameter mutation with no output schema, the description covers the essential unknowns: what the queue does, how to recover a stuck land, and how asynchronous results surface via watch.next.args/watch.done plus the host-notification requirement. What remains thin is failure behavior (e.g. rejected or unmergeable stacks) and why the destructive flag applies.

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 coverage is 0% and the single parameter is only a minLength-1 string, so the schema adds nothing beyond the name. The description contributes the meaningful constraint that the stack must be 'owned', implying an ownership precondition on stack_id, but gives no format or discovery hint (e.g. from stack_list).

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 ('Send one owned stack to the Mergestorm merge queue') and immediately explains the outcome ('tests it and lands it when its checks pass'). It also distinguishes itself from the sibling stack_restack by assigning restart handling there, so an agent can separate the two without opening schemas.

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 a clear when-to-use rule for the restart case: 'To restart a failed or stuck land, call stack_restack first and then this.' It does not explicitly cover adjacent situations such as checking progress (queue_status) or when enqueueing is inappropriate, but the primary alternative is named with its triggering condition.

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