Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

merge_feature_branches

Destructive

Records a merge between source and target feature branches and opens an interactive 3D stage on the merged result for orbit and zoom inspection.

Instructions

Record a merge — a = source.head, b = target.head. Opens Kiln's interactive inline 3D stage on the result (orbit/zoom panel in MCP Apps hosts; hosted sessions add a browser stage link).

Needs Kiln Pro.

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>",
      "merged_feature_version_id": "<merged_feature_version_id>"
    },
    "name": "merge_feature_branches"
  }
}

Input Schema

NameRequiredDescriptionDefault
merged_byNoWho performs the merge. Omit it to use the caller's own identity: on Kiln's servers the signed-in account (a different name is refused), locally the declared operator or the computer's user name. On a team-owned feature the caller needs push rights, or the merge is refused.
resolutionsNoHow conflicts were resolved, as a mapping of text to text, stored on the merge record as given; this tool does not apply or check it. Omit it to store none.
source_branch_idYesId of the feature branch being merged in.
target_branch_idYesId of the feature branch being merged into; its head moves to ``merged_feature_version_id``. The merge is refused if that head moved while the merge was being recorded (``CONCURRENT_MODIFICATION``).
merged_feature_version_idYesId of the existing feature version that is the result of the merge.
ancestor_feature_version_idNoFeature version id of the common ancestor. When given, the two branch heads are compared against it and any conflicts are stored on the merge record. Omit it to record the merge with no conflict report.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.5.1
    • addedInput schema / properties / ancestor_feature_version_id / description
      Added value: +"Feature version id of the common ancestor.  When given, the two branch heads are compared against it and any conflicts are stored on the merge record.  Omit it to record the merge with no conflict report."
    • addedInput schema / properties / merged_by / description
      Added value: +"Who performs the merge.  Omit it to use the caller's own identity: on Kiln's servers the signed-in account (a different name is refused), locally the declared operator or the computer's user name.  On a team-owned feature the caller needs push rights, or the merge is refused."
    • addedInput schema / properties / merged_feature_version_id / description
      Added value: +"Id of the existing feature version that is the result of the merge."
    • addedInput schema / properties / resolutions / description
      Added value: +"How conflicts were resolved, as a mapping of text to text, stored on the merge record as given; this tool does not apply or check it.  Omit it to store none."
    • addedInput schema / properties / source_branch_id / description
      Added value: +"Id of the feature branch being merged in."
    • addedInput schema / properties / target_branch_id / description
      Added value: +"Id of the feature branch being merged into; its head moves to ``merged_feature_version_id``.  The merge is refused if that head moved while the merge was being recorded (``CONCURRENT_MODIFICATION``)."
  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 safety profile is known. The description adds two useful behaviors beyond annotations: the Kiln Pro gate and the side effect of opening an interactive 3D stage with automatic decimation of oversized meshes. However, it omits the core mutation consequence (target head moves to the merged version) and that resolutions are stored but not applied, both of which live only in the schema.

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?

Roughly two-thirds of the text is a dedicated INLINE 3D STAGE paragraph about viewer panels and decimation, which is peripheral to recording a merge and appears boilerplate. The actual purpose is compressed into one fragment before the padding, so the description is not front-loaded around what the agent needs to invoke the tool correctly.

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?

The rich input schema covers branch IDs, identity/push-rights refusal, conflict report storage, and concurrency refusal, so the description does not need to repeat all of that. It adds the Pro entitlement and the stage side effect, but with no output schema it says nothing about what the merge record contains or how conflicts are surfaced, and it never routes the agent to the conflict-detection sibling.

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 the parameters are already well documented, including the CONCURRENT_MODIFICATION refusal on target_branch_id. The description's 'a = source.head, b = target.head' is a light restatement and adds no syntax, format, or validation detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 clear verb and resource ('Record a merge') and pins the semantics with 'a = source.head, b = target.head'. It does not differentiate from close siblings such as detect_feature_merge_conflicts, merge_design_branches, or source_merge_three_way, and the following paragraph shifts focus to a 3D viewer rather than the merge operation.

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 only usage-relevant statement is 'Needs Kiln Pro', which is a prerequisite rather than guidance. There is no indication of when to call this versus detect_feature_merge_conflicts (likely a pre-check), source_merge_three_way, or the design/decoration preset merge siblings, and no exclusions are given.

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