Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Get stack status

stack_status
Read-onlyIdempotent

Fetch an owned Mergestorm stack's enriched checks, agent state, attention, issues, and current candidate from its merge queue and blocker rules to see what needs repair, waiting, or human action.

Instructions

Fetch one owned Mergestorm stack with enriched checks and agent state, plus attention, issues, and currentCandidate from the same blocker rules as stack_wait, read against that stack's own merge queue. trunkBranch is mg-stack- for an adopted 2+ PR stack and matches the bottom open PR's GitHub base; an mg-park-* parentBranch is a freeze. Neither is drift to fix. repair names the concrete fix for attention; landGatePending is a wait, not attention. held names a blocker no agent run clears while Vortex or Cyclone is still busy on that PR (actAfter agents_idle, waitingOn); repair then describes the fix to plan, not to apply yet. Auto land off after a merge_failed, gh_error, or ci_timeout bounce (the stack's autoLandOff reads reason bounced) returns attention with the blocker "Auto land off after bounce", the bounce in issues[], and a repair of kind auto_land_off: fix the cause, then turn Auto land back on or enqueue. auto_land_switched_off (returned only when the PR has no live blocker of its own): Auto land was switched off without a bounce (queue entry cancelled, or nothing left to land); do not patch, push or turn it back on yourself, tell the human. A Vortex request_changes handoff at the live head returns attention with blocker "Vortex findings need a person" and repair kind vortex_findings; verify its findings against the live head. Attention covers every open layer, parked ones included, not only currentCandidate: it names the lowest layer with a blocker an agent must fix and no Vortex or Cyclone run working on it, and once that blocker clears the next read names the next blocked layer. 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_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
stack_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety bar is covered; the description adds genuinely non-obvious semantics: attention names the lowest layer with an agent-fixable blocker and moves as blockers clear, held means no agent run clears it, landGatePending is a wait not attention, and mg-park-* is a freeze not drift. It does not contradict the read-only annotation and even warns 'do not patch, push or turn it back on yourself'. It omits error/failure behavior of the call itself, keeping it below a 5.

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 purpose is front-loaded, but the remainder is a dense, unparagraphed run of jargon-laden clauses (trunkBranch, mg-park-*, landGatePending, auto_land_switched_off, vortex_findings) that is hard to scan. Each clause carries real information, so little is truly wasted, but the structure forces the reader to untangle output-field semantics and edge cases in one block.

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?

With no output schema, the description takes on the burden of explaining the return surface and does so at length: attention, issues, currentCandidate, repair, trunkBranch, parentBranch, held, landGatePending, and the auto-land bounce reasons. For a tool this behaviorally complex, the main remaining gap is argument-level detail (stack_id) and failure handling, not the semantics of what comes back.

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

Parameters2/5

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

There is one parameter, stack_id, with 0% schema description coverage, and the description never explains its format, where to obtain it (e.g., from stack_list), or what happens with a non-owned or invalid id. The only hint is the word 'owned', which implies an ownership constraint but is not stated as a requirement on the argument. With the schema silent, the description should have compensated and does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause states a specific verb and resource: 'Fetch one owned Mergestorm stack with enriched checks and agent state, plus attention, issues, and currentCandidate.' It also signals scope ('one owned stack') and ties its blocker rules to stack_wait, which sharpens its identity. It stops short of explicitly saying how it differs from stack_wait or stack_list in selection terms, leaving that inference to the reader.

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 clear operational context: 'Follow watch.next.args until watch.done' and 'background watching requires a confirmed host notification', plus 'See server instructions'. It also repeatedly tells the agent what to do with specific return states (auto_land_off: fix cause then re-enable; auto_land_switched_off: tell the human; held: plan, don't apply yet). There are no explicit when-not-to-use statements or direct sibling routing, but the context is strong.

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