Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

remove_mesh_floating_regions

Destructive

Clean downloaded or marketplace STL models by detecting and removing small disconnected floating geometry, such as support pillars and internal fragments, keeping the main mesh intact.

Instructions

Remove small disconnected components (floating geometry).

        Downloads and marketplace models often contain support pillars,
        internal fragments, or other floating geometry.  This tool
        identifies connected components and removes the small ones.

        :param file_path: Path to the STL file.
        :param output_path: Output path (defaults to overwriting input).
        :param keep_largest: Keep only the largest component (default True).
        :param min_triangle_pct: Min triangle % to keep (when keep_largest=False).
        :returns: Dict with removal statistics.

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": {
      "file_path": "<file_path>"
    },
    "name": "remove_mesh_floating_regions"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_pathYesPath to the STL file.
output_pathNoOutput path (defaults to overwriting input). Default: "".
keep_largestNoKeep only the largest component (default True). Default: true.
min_triangle_pctNoMin triangle % to keep (when keep_largest=False). Default: 1.0.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.5.1
    • addedInput schema / properties / file_path / description
      Added value: +"Path to the STL file."
    • changedInput schema / properties / keep_largest / description
      Previous value: -"Default: true."New value: +"Keep only the largest component (default True). Default: true."
    • changedInput schema / properties / min_triangle_pct / description
      Previous value: -"Default: 1.0."New value: +"Min triangle % to keep (when keep_largest=False). Default: 1.0."
    • changedInput schema / properties / output_path / description
      Previous value: -"Default: \"\"."New value: +"Output path (defaults to overwriting input). Default: \"\"."
  2. Changed6 schema fields changedv1.5.0
    • removedInput schema / properties / keep_largest / default
      Removed value: -true
    • addedInput schema / properties / keep_largest / description
      Added value: +"Default: true."
    • removedInput schema / properties / min_triangle_pct / default
      Removed value: -1
    • addedInput schema / properties / min_triangle_pct / description
      Added value: +"Default: 1.0."
    • removedInput schema / properties / output_path / default
      Removed value: -""
    • addedInput schema / properties / output_path / description
      Added value: +"Default: \"\"."
  3. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already carry destructiveHint=true and a mutation profile, but the description adds genuinely non-obvious behavior: output_path defaults to overwriting the input file, the call returns a dict of removal statistics, and the tool opens an inline 3D stage with automatic decimation of oversized meshes. That is real operational context beyond the structured fields; it stops short of stating failure modes or what happens to the input mesh topology.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is well front-loaded in the first two sentences, and the stage paragraph carries non-trivial information. However, the ':param' block duplicates the schema field-for-field and the ':returns'/'INLINE 3D STAGE' prose is verbose, so a meaningful share of the text does not earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter destructive mesh operation with no output schema, the description covers the essential ground: what it removes, that it overwrites the input by default, and that results come back as removal statistics. Missing are prerequisites (does the file need to be watertight?) and any statement of what 'small' means quantitatively beyond the parameter default.

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 documents all four parameters. The ':param' block in the description restates them nearly verbatim, adding only the conditional note that min_triangle_pct applies 'when keep_largest=False' — a nuance the schema already encodes in its own description. Baseline 3 for full-coverage duplication.

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 description states a specific verb and resource — 'removes small disconnected components' — and adds the diagnostic context ('support pillars, internal fragments, or other floating geometry') plus the mechanism ('identifies connected components and removes the small ones'). This implicitly separates it from split_mesh_by_component, but no sibling is named explicitly, so an agent must infer the boundary rather than being routed.

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?

Usage is implied through a scenario ('Downloads and marketplace models often contain support pillars...'), which tells the agent roughly when this applies. There is no explicit when-not guidance and no reference to alternatives such as repair_mesh, simplify_mesh_model, or split_mesh_by_component, so the agent gets context but no routing rules.

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