Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

cherry_pick_decoration_modification

Apply a single field change from a source preset version onto a target version, then open an interactive 3D stage to inspect the result.

Instructions

Apply ONE field modification from source onto target. 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": {
      "ancestor_preset_version_id": "<ancestor_preset_version_id>",
      "source_preset_version_id": "<source_preset_version_id>",
      "target_preset_version_id": "<target_preset_version_id>",
      "feature_id": "<feature_id>"
    },
    "name": "cherry_pick_decoration_modification"
  }
}

Input Schema

NameRequiredDescriptionDefault
feature_idYesThe field change to pick, e.g. ``"field:depth_mm"``, as listed by ``list_decoration_cherry_pick_candidates``. A field the source did not change is refused (``FEATURE_NOT_FOUND``).
source_branch_idNoId of the source branch, recorded on the picked change for provenance. Omit it to record none.
source_preset_version_idYesPreset version id holding the change to pick.
target_preset_version_idYesPreset version id the change is applied onto.
ancestor_preset_version_idYesPreset version id of the common ancestor of source and target.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.5.1
    • addedInput schema / properties / ancestor_preset_version_id / description
      Added value: +"Preset version id of the common ancestor of source and target."
    • addedInput schema / properties / feature_id / description
      Added value: +"The field change to pick, e.g. ``\"field:depth_mm\"``, as listed by ``list_decoration_cherry_pick_candidates``.  A field the source did not change is refused (``FEATURE_NOT_FOUND``)."
    • addedInput schema / properties / source_branch_id / description
      Added value: +"Id of the source branch, recorded on the picked change for provenance.  Omit it to record none."
    • addedInput schema / properties / source_preset_version_id / description
      Added value: +"Preset version id holding the change to pick."
    • addedInput schema / properties / target_preset_version_id / description
      Added value: +"Preset version id the change is applied 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?

The description does add real behavior beyond the annotations: the Kiln Pro entitlement gate, the side effect that an interactive 3D stage opens on success, automatic decimation of oversized meshes, and a browser-link fallback for hosts without MCP Apps. It does not cover failure modes (only the schema notes FEATURE_NOT_FOUND) or whether the pick creates a new version or mutates the target in place, which matters for a destructiveHint=false mutation.

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 core sentence is well front-loaded, but the inline-3D-stage behavior is stated twice almost verbatim (once as a parenthetical after sentence one, again in a full paragraph under "INLINE 3D STAGE"), and the all-caps heading plus the closing remark about the PNG preview being "the floor" add no selection value. Roughly half the text is redundant.

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?

Annotations cover the safety profile and the schema covers all five parameters, so the essentials are present. Given there is no output schema, though, the description never says what comes back (a new preset version id? a modified target?) or how conflicts are surfaced — a noticeable gap for a 4-required-param mutation.

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 schema already explains feature_id, source/target/ancestor version ids and the optional source_branch_id provenance field. The description contributes only the emphasis that exactly ONE field is applied per call — useful, but marginal against a fully documented schema.

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 field modification from source onto target" gives a specific verb and operation, and the decoration/preset framing distinguishes it from the sibling cherry-pick tools (cherry_pick_modification, cherry_pick_feature_modification). It never names those siblings explicitly, but the resource domain is unambiguous.

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 context offered is the gating note "Needs Kiln Pro." There is no guidance on when to pick this versus the plain or feature cherry-pick tools, no mention that candidates must first come from list_decoration_cherry_pick_candidates (that hint lives only in the schema), and no preconditions about ancestor/source/target version alignment.

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