Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

create_geometry_collection

Destructive

Create and save a UGeometryCollection asset at a package path, optionally populated from a StaticMesh; an existing collection is reset and rebuilt.

Instructions

Creates a UGeometryCollection asset at package_path/name, optionally filled from one StaticMesh, and saves it. An existing collection there is RESET first (all geometry and sources discarded; created false, rebuilt true). A source_mesh_path that does not load as a StaticMesh is an error, checked before anything is touched. Succeeds only when the package reaches disk; a failed save leaves the collection in memory only (saved false, save_error).

Returns: { asset_path: string, geometry_collection_name: string, num_materials: int, num_transforms: int, created: bool, rebuilt: bool, saved: bool, save_error: string? }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName of the geometry collection asset, e.g. GC_Wall
package_pathYesContent folder for the asset, e.g. /Game/Chaos/Collections; a path without a leading slash is placed under /Game/
source_mesh_pathNoOptional StaticMesh to convert and append, e.g. /Engine/BasicShapes/Cube

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.0
    • changedInput schema / properties / package_path / description
      Previous value: -"Package path for the asset, e.g. /Game/Chaos/Collections"New value: +"Content folder for the asset, e.g. /Game/Chaos/Collections; a path without a leading slash is placed under /Game/"
  2. First observedv1.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses that an existing collection is destroyed (created false, rebuilt true), that mesh validation happens before any mutation, and that a failed save leaves the asset in memory only. The destructiveHint=true annotation is consistent with this.

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

Conciseness5/5

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

Front-loaded with the primary action, then the overwrite risk, then error/save semantics, then the return shape. Every sentence carries distinct information and there is no wasted phrasing.

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

Completeness5/5

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

With no output schema present, the inline Returns block is necessary and supplied. For a destructive, non-idempotent creation tool, the reset behavior, validation ordering, and save-failure outcome give the agent everything needed to call it correctly.

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?

With 100% schema coverage the baseline is 3, but the description adds real meaning: package_path/name are composed into the asset path, and a source_mesh_path that fails to load as a StaticMesh is a hard error. It reinforces rather than merely repeats the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Creates) and resource (UGeometryCollection asset) with exact location semantics (package_path/name) and optional mesh-fill. It is clearly separable from siblings such as create_collection, add_geometry_collection_source, and fracture_geometry_collection.

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

Usage Guidelines4/5

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

Explains when source_mesh_path applies ('optionally filled from one StaticMesh') and warns that an existing collection at the path is reset, which affects the decision to call it. It stops short of naming alternative tools or stating an explicit when-not-to-use condition.

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