Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

list_instance_overrides

Read-onlyIdempotent

Audit a placed actor against its archetype to list per-instance property overrides, confirming whether edits actually landed on the instance.

Instructions

Audit a PLACED ACTOR (and every one of its components) against its ARCHETYPE and list the property values that were authored as per-instance overrides in the level, each with its archetype baseline, plus the physical package that carries them (the rotating-hash OFPA .uasset for a World Partition actor) and whether that package is dirty. The tool that answers "did my write actually land on this instance, or only look like it?" — it catches set_property_value reporting success on an FGameplayTag while storing an empty "()" override. Component baselines are the SCS TEMPLATE, not the Blueprint CDO (a CDO carries no SCS components at all). Resolves in the EDITOR world by design: an instance override is an on-disk concept, not a runtime one.

Returns: { actor_path, actor_name, actor_label, actor_class, archetype_path, archetype_class, archetype_is_cdo, is_package_external, package_name, package_file, package_file_exists, package_dirty, overrides: [{property, kind, value, archetype_value, declaring_class, property_type, note, ...}], override_count, components: [{component, component_class, creation_method, archetype_path, archetype_is_cdo, overrides, override_count, noise?}], components_examined, component_override_count, total_override_count, properties_examined, skipped: {transient, not_edit, no_baseline}, noise_counts: object, noise_count: int, noise?: [...], caveat: string }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actorYesActor to audit: internal object name, editor label, or full object path. Resolved in the EDITOR world — a per-instance override is an editor/on-disk concept, not a runtime one.
require_editNoOptional (default true). Only consider properties flagged CPF_Edit, i.e. what a human could actually have authored in the details panel. false widens to every reflected property.
include_noiseNoOptional (default false). Also list, under `noise[]`, the properties the engine considers EQUAL but whose exported text differs (FText localization identity, object outer). They are ALWAYS counted in `noise_counts` regardless.
include_transientNoOptional (default false). Include CPF_Transient / DuplicateTransient / NonPIEDuplicateTransient / Deprecated properties. They are never saved, so they are noise in an override audit.
include_componentsNoOptional (default true). Also diff every UActorComponent of the actor against C->GetArchetype() — the SCS template, NOT the Blueprint CDO (a BP CDO does not carry the SCS components at all, which is why a snapshot_object workaround yields an unusable component half).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover readOnly/idempotent/destructive safety, but the description adds substantive behavior: editor-world resolution by design, the SCS-template vs Blueprint-CDO baseline distinction, dirtiness of the OFPA package, noise/transient handling, and an explicit caveat field. This is rich context beyond the structured fields.

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

Conciseness4/5

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

Front-loads the core purpose in the first sentence and orders the caveats sensibly. The exhaustive Returns enumeration is long, but with no output schema it is defensible; it remains dense rather than padded.

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 complex audit tool with no output schema, the description supplies the return shape, the editor-world constraint, the baseline semantics, and caveats/noise behavior. An agent has everything needed to call it and interpret results 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 already 100% with detailed parameter descriptions, so the baseline is 3. The description goes further by explaining why include_components uses the SCS template rather than a CDO and why noise is always counted, adding meaning beyond 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 precise verb+resource ('Audit a PLACED ACTOR ... list the property values that were authored as per-instance overrides') and immediately scopes it (against its archetype, plus components). It is clearly distinguishable from siblings like set_property_value, snapshot_object, and diff_blueprint_components.

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 a strong when-to-use framing ('did my write actually land on this instance, or only look like it?') and names adjacent tools (set_property_value, snapshot_object) with the failure modes they miss. It does not state explicit when-not-to-use conditions, so it stops just short of a 5.

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