Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

cherry_pick_modification

Applies one isolated semantic modification from a source branch onto a target branch, then opens an interactive 3D stage to inspect the result. Use it to move a single design change between versions.

Instructions

Apply one isolated semantic modification from a source branch onto a target branch. 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": {
      "ancestor_version_id": "<ancestor_version_id>",
      "source_version_id": "<source_version_id>",
      "target_version_id": "<target_version_id>",
      "feature_id": "<feature_id>"
    },
    "name": "cherry_pick_modification"
  }
}

Input Schema

NameRequiredDescriptionDefault
feature_idYesThe modification to pick, by the id ``list_cherry_pick_candidates`` listed.
source_branch_idNoOptional source branch identifier for provenance tagging.
source_version_idYesThe source-branch version that contains the modification to extract.
target_version_idYesThe target-branch head to apply onto.
ancestor_version_idYesDesign version id of the common ancestor of source and target. All three versions need a recorded mesh fingerprint, or the call returns ``FINGERPRINT_UNAVAILABLE``.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.5.1
    • addedInput schema / properties / ancestor_version_id / description
      Added value: +"Design version id of the common ancestor of source and target.  All three versions need a recorded mesh fingerprint, or the call returns ``FINGERPRINT_UNAVAILABLE``."
    • addedInput schema / properties / feature_id / description
      Added value: +"The modification to pick, by the id ``list_cherry_pick_candidates`` listed."
    • addedInput schema / properties / source_branch_id / description
      Added value: +"Optional source branch identifier for provenance tagging."
    • addedInput schema / properties / source_version_id / description
      Added value: +"The source-branch version that contains the modification to extract."
    • addedInput schema / properties / target_version_id / description
      Added value: +"The target-branch head to apply onto."
  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 readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is partly covered. The description does add real behavior beyond that: the tool opens an inline 3D stage on success, hosted sessions attach a browser stage link, and oversized meshes are auto-decimated. It omits more relevant mutation behavior, though — whether a new target version is created, what happens on conflicts, and whether the operation is reversible.

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 first sentence is well front-loaded, but the rest is largely marketing: a tier table with bullet separators and a multi-sentence INLINE 3D STAGE block that repeats the stage behavior already stated in sentence two. Roughly half the text is redundant or promotional rather than decision-relevant.

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 non-destructive mutation tool with full schema coverage and no output schema, the description covers the side effect (3D stage) and entitlement gating. It is incomplete on the things an agent most needs: how this differs from the sibling cherry-pick tools, and what the result of a successful pick looks like (new version id, conflict handling).

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 five parameters (including the ancestor fingerprint precondition and FINGERPRINT_UNAVAILABLE error) are already documented in the schema. The description adds no parameter-level meaning beyond noting the modification is "isolated", 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?

"Apply one isolated semantic modification from a source branch onto a target branch" gives a specific verb (apply) and resource (a single semantic modification), and the word "isolated" conveys the cherry-pick scope. It does not, however, distinguish itself from the near-identical siblings cherry_pick_feature_modification and cherry_pick_decoration_modification, so an agent cannot tell which cherry-pick variant to pick from the description 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 when-to-use / when-not-to-use guidance and no named alternative among the three cherry-pick siblings or the merge_* tools. The only conditional content is a plan-tier entitlement table (Free/Pro/Business/Enterprise), which is a licensing constraint rather than invocation guidance; the prerequisite of obtaining feature_id from list_cherry_pick_candidates appears only in the schema, not here.

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