Skip to main content
Glama

inspect_object

Read-onlyIdempotent

Profile an Unreal object in one call: get identity, class metadata, every reflected property, and live actor components from editor or live PIE worlds.

Instructions

One-shot portrait of an object instance: identity (name, class, class path, is_valid), the class-level flags/metadata/implemented interfaces, EVERY reflected property as a { name: typed_value } map, and — when it is an actor — the list of its live components with their classes. The "I know nothing about this object yet" entry point; once you know what you want, get_property_value / get_properties are far cheaper, list_object_properties adds per-property editor metadata the map here omits, and get_actor_components lists components alone. Accepts world, so the portrait can be taken of the LIVE server instance or of the client one, and the response stamps which world answered.

Returns: { object_path: string, object_name: string, class_name: string, class_path: string, is_valid: bool, is_abstract, is_deprecated, is_placeable, is_native, config_name, implemented_interfaces: [{interface, implemented_by_k2}], class_group?, is_blueprintable?, is_blueprint_type?, display_name?, tooltip?, properties: {prop_name: typed_value}, components: [{name, class}], world: string, world_name: string|null, world_package: string|null, world_type: string|null, net_mode: string|null, pie_instance: number }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
worldNoOptional world selector: absent/'editor' (default: the editor/asset instance) | 'pie' (ambiguous: PlayWorld, else the first PIE context) | 'server' (the PIE world with authority) | 'client' | 'pie:N' | 'game' (alias of 'pie'). Anything other than absent/'editor' portrays the LIVE instance in that world; an UNRECOGNIZED value is an error naming the worlds that exist, never a silent fallback to another world.
object_pathYesPath or name of the object to inspect. In the editor world: full object path, asset path, CDO/archetype, or a dotted "Actor[.Component[.Subobject]]" whose first segment is the actor's INTERNAL name. In a live world: a fully-qualified PIE path or the same dotted form (first segment matches internal name OR editor label).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real context: it can target either the LIVE or editor instance, and the response stamps which world answered, plus the relative cost versus narrower getters. It stops short of describing pagination or failure modes beyond that, but the world/breadth semantics are meaningfully disclosed.

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 the identity of the operation and its component parts, then routes to alternatives, then the return shape. It is on the long side and the return-shape dump duplicates the world-selection point already made, but in the absence of an output schema that detail earns its place.

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, the description carries the full burden of return-value documentation and does so exhaustively (object_path, class fields, flags, interfaces, properties map, components, world identity, net_mode, pie_instance). Nothing an agent needs to call it correctly 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 coverage is 100% and the world/object_path descriptions already document defaults, aliases, accepted path forms, and error-on-unrecognized-value behavior. The description only reiterates the live-vs-editor world choice and that the response stamps the answering world, adding little beyond the schema. Baseline 3 is appropriate.

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 action ('one-shot portrait of an object instance') and enumerates exactly what the portrait contains: identity, class flags, all reflected properties, and actor components. It explicitly distinguishes itself from siblings like get_property_value, list_object_properties, and get_actor_components, so an agent can select it without opening the 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?

Declares itself 'the "I know nothing about this object yet" entry point' and then names the cheaper/specialized alternatives with the conditions that select them ('once you know what you want, get_property_value / get_properties are far cheaper'). When-to-use, when-not-to-use, and alternatives are all explicit.

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