Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

rebase_design_branch

Destructive

Replay a design branch's divergent versions onto another branch to unify changes, then open the result in Kiln's interactive 3D stage for orbit and zoom review.

Instructions

Rebase a design branch's divergent versions onto another. 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>",
      "onto_branch_id": "<onto_branch_id>"
    },
    "name": "rebase_design_branch"
  }
}

Input Schema

NameRequiredDescriptionDefault
operatorNoWho is performing the rebase, recorded on the event. 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.
onto_branch_idYesId of the design branch the replayed versions are appended to; its head ends at the source branch's head. Must be a different branch in the same graph.
source_branch_idYesId of the design branch whose versions above the common ancestor are replayed, oldest first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.5.1
    • addedInput schema / properties / onto_branch_id / description
      Added value: +"Id of the design branch the replayed versions are appended to; its head ends at the source branch's head.  Must be a different branch in the same graph."
    • addedInput schema / properties / operator / description
      Added value: +"Who is performing the rebase, recorded on the event. 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."
    • addedInput schema / properties / source_branch_id / description
      Added value: +"Id of the design branch whose versions above the common ancestor are replayed, oldest first."
  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 covered. The description adds genuinely non-obvious behavior: the inline 3D stage is opened on success, hosted sessions get a browser stage link, and oversized meshes are auto-decimated. It omits the behavior that matters most for a history rewrite — what happens on conflicts, whether the operation is atomic, and whether existing head state is recoverable via undo_last_head_change.

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 purpose is correctly front-loaded, but the inline 3D stage is explained twice in near-identical terms (a capitalised INLINE 3D STAGE section restating paragraph one), and the closing line 'the PNG preview is the floor, not the whole experience' is promotional rather than informative. The tier list consumes space without helping the agent decide or call.

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 a destructive, history-rewriting tool with no output schema, the description should cover conflict handling, failure semantics, and recoverability; none are present. It does cover the observable side effect (the 3D stage) and plan gating, so it is not wholly inadequate, but the agent lacks enough to predict outcomes on conflict.

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%, and the schema already explains source_branch_id replay order, onto_branch_id head semantics, and the same-graph constraint, so baseline 3 applies. The description adds nothing about parameters and does not mention the optional 'operator' argument or its signed-in-account restriction.

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 first sentence states a specific verb and resource ('Rebase a design branch's divergent versions onto another'), which cleanly separates it from merge_design_branches and from the naming-convention siblings rebase_feature_branch and rebase_preset_branch. It stops short of explicitly naming those alternatives, so an agent must infer the design/feature/preset distinction from the resource noun alone.

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?

There is no statement of when to rebase versus when to merge, no mention of prerequisites such as a common ancestor or a clean working state, and no failure/conflict conditions. The tier block ('Free: Branch · merge · cherry-pick · undo...') communicates plan availability rather than tool-selection guidance, which is a different concern.

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