Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

merge_design_branches

Destructive

Merge a source design branch into a target, record conflict resolutions, and open an interactive 3D stage to inspect the merged result.

Instructions

Record a merge of source into target with conflict resolution. Opens Kiln's interactive inline 3D stage on the result (orbit/zoom panel in MCP Apps hosts; hosted sessions add a browser stage link).

Free door, tiered answer — Free: Branch · merge · cherry-pick · undo, on the designs you keep · Pro: Branch · merge · cherry-pick · undo, on every design · Business: ✓ · Enterprise: ✓.

INLINE 3D STAGE: on success this tool opens Kiln's interactive 3D stage — an inline viewer panel the user can orbit, zoom, and turn over — in hosts that render MCP Apps panels (Kiln's hosted connection attaches a browser stage link for hosts that don't). Oversized meshes are decimated automatically for the stage; the PNG preview is the floor, not the whole experience.

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": {
      "source_branch_id": "<source_branch_id>",
      "target_branch_id": "<target_branch_id>"
    },
    "name": "merge_design_branches"
  }
}

Input Schema

NameRequiredDescriptionDefault
pr_idNoOptional explicit pull-request id to satisfy the gate with. Omitted → the open/approved PR on this exact source→target pair is used.
merged_byNoUser identifier for audit (server-verified against the authenticated session; derived from JWT).
resolutionsNoAnswers to the merge's open questions, ``{item_id: choice}``, where a choice is ``prefer_branch_a`` (the source), ``prefer_branch_b`` (the target), ``apply_neither``, a branch's name or ``original``; ``{"*": choice}`` answers every item not named. Omit it when ``detect_merge_conflicts`` reported ``ready``.
merge_strategyNoHow the merged version was composed, recorded on the merge: ``semantic`` (the default), ``source``, ``mesh_boolean``, ``source_with_conflicts``, ``user_curated`` or ``sketch``. Any other value, the empty string included, is refused. A sketch-built part records ``sketch`` whatever is passed. Default: "semantic".
source_branch_idYesBranch supplying the changes.
target_branch_idYesBranch receiving the merge.
merged_version_idNoThe composed result. Omit it for a sketch-built part and Kiln builds it; required otherwise.
ancestor_version_idNoCommon ancestor for the mesh path (without it, mesh conflict detection is skipped). A sketch merge always reads from the true split point.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv1.5.1
    • addedInput schema / properties / ancestor_version_id / description
      Added value: +"Common ancestor for the mesh path (without it, mesh conflict detection is skipped).  A sketch merge always reads from the true split point."
    • changedInput schema / properties / merge_strategy / description
      Previous value: -"Default: \"semantic\"."New value: +"How the merged version was composed, recorded on the merge: ``semantic`` (the default), ``source``, ``mesh_boolean``, ``source_with_conflicts``, ``user_curated`` or ``sketch``.  Any other value, the empty string included, is refused.  A sketch-built part records ``sketch`` whatever is passed. Default: \"semantic\"."
    • addedInput schema / properties / merged_by / description
      Added value: +"User identifier for audit (server-verified against the authenticated session; derived from JWT)."
    • addedInput schema / properties / merged_version_id / description
      Added value: +"The composed result.  Omit it for a sketch-built part and Kiln builds it; required otherwise."
    • addedInput schema / properties / pr_id / description
      Added value: +"Optional explicit pull-request id to satisfy the gate with.  Omitted → the open/approved PR on this exact source→target pair is used."
    • addedInput schema / properties / resolutions / description
      Added value: +"Answers to the merge's open questions, ``{item_id: choice}``, where a choice is ``prefer_branch_a`` (the source), ``prefer_branch_b`` (the target), ``apply_neither``, a branch's name or ``original``; ``{\"*\": choice}`` answers every item not named.  Omit it when ``detect_merge_conflicts`` reported ``ready``."
    • addedInput schema / properties / source_branch_id / description
      Added value: +"Branch supplying the changes."
    • addedInput schema / properties / target_branch_id / description
      Added value: +"Branch receiving the merge."
  2. Addedv1.5.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this mutates state. The description does add genuine post-call behavior — an inline orbitable 3D stage, automatic mesh decimation for oversized results, and a browser stage link in non-panel hosts — but it never says what the destructive merge does to existing branches/versions or that an open/approved PR is required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The paragraph on the inline 3D stage is delivered twice — once parenthetically in the first section and again in the all-caps "INLINE 3D STAGE" block — and the tier/plan bullet reads as marketing copy rather than tool guidance. The useful core is one sentence buried ahead of substantial redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter destructive merge with no output schema, the description covers the post-success experience well but omits the workflow context an agent needs: the conflict-detection prerequisite, the PR gate satisfied by pr_id, and the consequences of the mutation. Combined with fully documented schema and destructive annotations, this is adequate but not complete.

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 all eight parameters are already documented in structured fields, including resolutions, merge_strategy, and merged_version_id. The description adds no parameter-level meaning of its own, which is acceptable at the baseline but no better.

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 sentence gives a specific verb and resource: "Record a merge of source into target with conflict resolution," which tells an agent exactly what operation is performed. However, it never distinguishes this tool from siblings such as merge_feature_branches, merge_decoration_preset_branches, or source_merge_three_way, so the agent must infer that this one operates on design branches specifically.

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

Usage Guidelines2/5

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

The description contains no when-to-use vs when-not guidance and never names an alternative tool or prerequisite, even though the schema implies a detect_merge_conflicts step and a PR gate. The tier list (Free/Pro/Business/Enterprise) describes plan entitlements rather than call conditions, so it does not help the agent decide whether to invoke this tool now.

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

Deploy Server

Other Tools