Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

duplicate_asset

Copies an Unreal asset to a new name in the same directory and saves it to disk, creating a safety copy before risky edits.

Instructions

Duplicates an asset to a new name in the same directory, then PERSISTS the copy to disk immediately (unless Play-In-Editor is active -- see the "saved"/"save_error" note on the save step below; a duplicate is very often used AS a safety net before a risky edit, so leaving it memory-only defeats the point). By default (remap_internal_refs absent/false) this is otherwise a plain copy: like EditorAssetLibrary.duplicate_asset, any internal references the copy holds still point at the ORIGINAL (not remapped). Set remap_internal_refs=true to run the SAME 2nd-pass reference remap that duplicate_directory uses (FArchiveReplaceObjectRef mapping original->copy) so the copy's own self-references point at the copy, before that save. repoint_parents_within additionally re-applies a MaterialInstance parent via SetParentEditorOnly when the parent maps into the copied set (for a single asset this only fires if the copy's parent is the original itself).

Returns: { original_asset_path: string, new_asset_name: string, new_asset_path: string, duplication_success: bool, duplication_message: string, new_asset_class: string, new_package_name: string, asset_verified: bool, new_file_size_bytes: number?, new_file_size_mb: number?, original_asset_class: string, original_package_name: string, new_path: string?, refs_remapped: int?, saved: bool?, save_error: string? }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
asset_pathYesFull asset path to duplicate (e.g. /Game/Assets/MyAsset)
new_asset_nameYesName for the duplicated asset
remap_internal_refsNoOptional bool (default false). When true, remap the copy's internal refs (original->copy) before the save; adds { new_path, refs_remapped } to the result.
repoint_parents_withinNoOptional bool (default false). When true (and remap_internal_refs true), also re-apply MaterialInstanceConstant parents that map into the copied set via SetParentEditorOnly.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: it discloses immediate disk persistence and the Play-In-Editor exception, the default non-remapped reference semantics, the opt-in remap pass, and the narrow condition under which repoint_parents_within fires. With destructiveHint=false and idempotentHint=false already present, this is rich, non-redundant behavioral disclosure.

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 core action is front-loaded, but the body is a single dense run-on paragraph with stacked parentheticals and ALL-CAPS emphasis that hurt readability. Most content earns its place, but the structure is unwieldy for a four-parameter tool.

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?

For a mutating duplicate tool this covers the full decision surface: persistence behavior, PIE caveat, reference remapping, parent repointing, and an inline 'Returns:' field list that compensates for the absent output schema. An agent has 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?

Schema coverage is 100% so the baseline is 3, and the description earns above that by explaining the consequences of each flag: remap_internal_refs changes whether the copy's refs point at the original or the copy, and repoint_parents_within only fires when the parent maps into the copied set. It adds meaning rather than restating the schema text.

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+resource plus scope: 'Duplicates an asset to a new name in the same directory.' It explicitly contrasts with EditorAssetLibrary.duplicate_asset and duplicate_directory, so an agent can distinguish it from the closest siblings without opening any schema.

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?

Gives clear context for when this is used ('very often used AS a safety net before a risky edit') and names the sibling whose behavior it mirrors (duplicate_directory). It does not, however, state an explicit rule for when to pick duplicate_asset over duplicate_directory, so the routing guidance is implied rather than spelled out.

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