Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

get_class_hierarchy

Read-onlyIdempotent

Trace a class’s full inheritance chain to UObject, listing each ancestor’s path, native/Blueprint status, flags, and interfaces. Answer “is X a Y?” to find where native code ends and Blueprint begins.

Instructions

Walk the full inheritance chain of a class from itself up to UObject, one record per level with its path, is_native flag, class flags/metadata and implemented interfaces — the answer to "is X a Y?" and "where does the native code stop and the Blueprint chain start?". get_blueprint_parent returns only the IMMEDIATE parent of a Blueprint ASSET; this returns every ancestor of a compiled CLASS. get_blueprint_children goes the other direction (descendants).

Returns: { class_name: string, hierarchy: [{name, path, is_native, is_abstract, is_deprecated, is_placeable, config_name, implemented_interfaces: [{interface, implemented_by_k2}], class_group?, is_blueprintable?, is_blueprint_type?, display_name?, tooltip?}] }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
class_nameYesUClass identifier, resolved with ResolveClass: bare FName ("Character"), /Script/Module.Class, a Blueprint asset path, or a generated class ("BP_MyActor_C"). WARNING: the REGISTERED FName can differ from the C++ type name and from the name the Python bindings expose — UMetaHumanCharacterInstance is registered as "MetaHumanInstance" — so a failure here is NOT evidence the class is absent; the error names the near misses instead. The response echoes what it resolved to in resolved_class_name / resolved_class_path.

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?

Beyond the readOnly/idempotent/non-destructive annotations, it discloses the resolution hazard (registered FName can differ from the C++/binding name, with a concrete MetaHuman example), clarifies that a resolution failure is not evidence of absence, and states that the response echoes resolved_class_name/resolved_class_path. That is meaningful behavioral context the annotations do not carry.

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-loaded with purpose and sibling routing, then a clearly delimited Returns block that is justified because there is no output schema. It is slightly long and the first sentence is dense, but every clause carries information.

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 one parameter, full schema coverage, and no output schema, the description supplies the missing return shape (hierarchy records and their fields) plus the resolution-failure caveat. Nothing an agent needs to invoke and interpret this call is missing.

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% and the class_name property already documents ResolveClass forms, the name-mismatch warning, and the echoed resolution fields, so the description adds essentially nothing new about the parameter. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

The first sentence names a specific verb ("walk"), the exact resource (full inheritance chain of a class up to UObject), and the per-level payload. It explicitly distinguishes itself from get_blueprint_parent (immediate parent only) and get_blueprint_children (descendants), so an agent can pick it 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 Guidelines5/5

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

It states when to use it versus the two nearest siblings and gives the selecting condition: get_blueprint_parent operates on a Blueprint ASSET and returns one level, while this returns every ancestor of a compiled CLASS. It also names the reverse direction tool, covering the alternative axis completely.

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