Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

cherry_pick_feature_modification

Isolate one modified feature field, project it onto a target design using the common ancestor, and open an interactive 3D stage to inspect the applied result.

Instructions

Isolate ONE modification and project the target fingerprint after applying. 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_feature_version_id": "<ancestor_feature_version_id>",
      "source_feature_version_id": "<source_feature_version_id>",
      "target_feature_version_id": "<target_feature_version_id>",
      "feature_field": "<feature_field>"
    },
    "name": "cherry_pick_feature_modification"
  }
}

Input Schema

NameRequiredDescriptionDefault
feature_fieldYesThe changed field to pick, as named in ``list_feature_cherry_pick_candidates``. A field the source did not change is refused (``FEATURE_FIELD_NOT_FOUND``), naming the fields that did change.
source_branch_idNoId of the source branch, recorded on the picked change for provenance. Omit it to record none.
source_feature_version_idYesFeature version id holding the change to pick.
target_feature_version_idYesFeature version id the change is projected onto.
ancestor_feature_version_idYesFeature 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_feature_version_id / description
      Added value: +"Feature version id of the common ancestor of source and target."
    • addedInput schema / properties / feature_field / description
      Added value: +"The changed field to pick, as named in ``list_feature_cherry_pick_candidates``.  A field the source did not change is refused (``FEATURE_FIELD_NOT_FOUND``), naming the fields that did change."
    • 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_feature_version_id / description
      Added value: +"Feature version id holding the change to pick."
    • addedInput schema / properties / target_feature_version_id / description
      Added value: +"Feature version id the change is projected onto."
  2. Addedv1.5.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description does disclose gating (Needs Kiln Pro) and a side effect (opens an inline 3D stage, decimating oversized meshes). It does not say whether the picked change is committed irreversibly, what happens on conflict, or what the projection result looks like beyond the fingerprint.

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 half the text is the 'INLINE 3D STAGE' block, which restates the same panel/link fact twice and buries the one-line core operation. The wrap-up 'improve_generation_prompt'-neutral sentence about PNG floor vs whole experience is marketing framing with no decision value for an agent.

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?

Covers gating and the stage side effect, which is more than most mutation tools get, but with no output schema the description should state what the projected fingerprint result contains and whether the pick is persisted or previewed. Conflict/refusal behavior is only implied via one schema error code.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description adds value by framing the operation as ancestor/source/target triple semantics, which clarifies how the four required IDs relate rather than just naming them. It does not, however, mention source_branch_id provenance recording.

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?

States a specific verb and resource: isolate ONE modification and project the target fingerprint after applying. This is clearly distinct from the many list_/get_ siblings. It doesn't explicitly name the sibling cherry-pick variants (cherry_pick_modification, cherry_pick_decoration_modification) that an agent would need to disambiguate, which prevents a 5.

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

Usage Guidelines3/5

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

The description implies usage ('isolate ONE modification') and the schema points at list_feature_cherry_pick_candidates for the field name, but there is no explicit when-to-use statement, no exclusion versus other cherry-pick tools, and no prerequisite sequencing (must have an ancestor, source, target already).

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