Skip to main content
Glama

inspect_subsystem_instance

Read-onlyIdempotent

Read exposed properties from a live Unreal subsystem instance by specifying its class and lifetime host, returning names, C++ types, edit/blueprint flags, and text values.

Instructions

Reads the exposed properties (EditAnywhere or Blueprint-visible, inherited included, Transient skipped) of a live subsystem instance, each with name, C++ type, property class, edit and blueprint_visible flags, and its value exported as text (empty when it cannot be exported). lifetime picks the host: world uses the editor world and gameinstance and localplayer its game instance, never PIE's, so those two fail when the editor world has none. A missing host or instance is an error. Read-only. For a quick existence check use get_subsystem_instance; to enumerate use list_subsystem_instances or list_local_player_subsystems.

Returns: { subsystem_class: string, lifetime: string, subsystem_name: string, subsystem_path: string, property_count: int, properties: [{ name, cpp_type, class, edit, blueprint_visible, value }] }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lifetimeYesWhich host resolves the instance: one of engine | gameinstance | world | editor | localplayer.
player_indexNoLocal player index, used only when lifetime is "localplayer" (default 0).
subsystem_classYesClass name of the subsystem to inspect (short reflected name or /Script path).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (which already assert readOnly/idempotent), the description discloses the property-inclusion filter rules, that values are exported as text and left empty when not exportable, the host-resolution semantics per lifetime, the deliberate exclusion of PIE instances, and that a missing host or instance is an error. This is substantial behavior 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 what the tool does, then lifetime behavior, error condition, sibling routing, and the return shape. Every sentence is load-bearing, but the body is a single dense run-on paragraph, slightly reducing scanability.

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 read/inspect tool with no output schema it fully compensates by describing the returned object shape inline, and it covers property filters, host-resolution edge cases, and failure modes. 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, but the description adds real meaning beyond the schema for lifetime by explaining how each value resolves (world->editor world; gameinstance/localplayer->game instance, never PIE). player_index is left to the schema, which documents it, so it does not fully reach 5.

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 (reads/inspect) and resource (exposed properties of a live subsystem instance), and narrows scope precisely with the property filters (EditAnywhere/Blueprint-visible, inherited included, Transient skipped). It clearly distinguishes itself from the sibling read tools by naming exactly which ones do existence checks or enumeration instead.

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?

Explicit routing is given: 'For a quick existence check use get_subsystem_instance; to enumerate use list_subsystem_instances or list_local_player_subsystems.' It also states when the tool fails (missing host/instance; world/gameinstance/localplayer resolve non-PIE hosts), which is genuine when-to-use/when-not guidance.

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