Skip to main content
Glama

Prepare a merge plan

argon_merge_preview

Computes and stores a reviewable merge plan (data pull request) for a branch, returning its plan ID so users can inspect changes before merging or discarding.

Instructions

Compute and persist a reviewable merge plan (a data pull request). Returns the plan ID.

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": {
      "project": "<project>",
      "branch": "<branch>"
    },
    "name": "argon_merge_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
branchYesBranch to merge into its parent
projectYesProject name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.8.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false. The description adds real context beyond them: the tool persists state server-side (creating an artifact, not just reading) and hands back a plan ID. It still omits whether repeated calls create duplicate plans, whether plans expire, and any permission requirements.

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?

Two compact clauses, zero filler: the action and artifact come first and the return value last. Every word earns its place.

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 two-parameter tool with no output schema, an agent learns what is produced, that it is persisted, and that a plan ID comes back. The main remaining gap is how the plan relates to subsequent apply/diff calls, which would round it out.

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 100%, so both parameters (project, branch) are already documented, including that branch is merged into its parent. The description adds no meaning beyond that, so the baseline of 3 applies.

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?

States a specific verb pair (compute and persist) and a concrete resource (a reviewable merge plan, glossed as a data pull request), plus the return value. The 'preview/plan' framing implicitly separates it from argon_merge_apply, though it never names that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The word 'reviewable' and the returned plan ID imply this is the step that precedes applying a merge, but the description never states when to use it, when not to, or that argon_merge_apply is the follow-on. Guidance is inferable rather than explicit.

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