Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

disconnect_pcg_nodes

DestructiveIdempotent

Removes a directed edge between two PCG node pins in an Unreal PCG Graph and re-saves the asset. Reports already_disconnected if no such edge exists.

Instructions

Removes the directed edge between two PCG nodes' pins. Pin labels default to the node's "Out"/"In" pin (else its first pin) and the resolved labels are echoed. Idempotent: if no such edge exists it reports already_disconnected without error. The graph is re-saved after an edge is removed.

Returns: { graph_name: string, asset_path: string, from_node: string, from_pin: string, to_node: string, to_pin: string, already_disconnected: bool, removed: bool, disconnected: bool, edge_count: int, saved: bool, save_error: string }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
to_pinNoOptional input-pin label on to_node (default the node's "In" pin, else its first input pin).
to_nodeYesDownstream node name, or the token "Output".
from_pinNoOptional output-pin label on from_node (default the node's "Out" pin, else its first output pin).
from_nodeYesUpstream node name, or the token "Input".
pcg_graph_pathYesAsset path of the PCG Graph (e.g. "/Game/PCG/PCG_Example").

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations cover the safety profile (destructive, not read-only, idempotent), so the description adds value by specifying the pin-label defaults and the graph re-save behavior. The return structure is fully detailed, which is helpful given no output schema.

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?

The description is front-loaded with the core action, followed by pin label defaults, idempotency behavior, and a detailed return structure. It's efficient, though the return object could be more compactly represented.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and 100% parameter coverage, the description is quite complete. It covers the action, idempotency, side effects (graph re-save), and returns. A note about permissions or file locking might be the only missing behavioral detail.

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%, so parameter meanings are already documented. The description adds the pin-label default logic ('Out'/'In' or first pin) which is useful, but the schema descriptions already cover most of this.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: removes a directed edge between two PCG nodes' pins. This distinguishes it from connect_pcg_nodes, but doesn't explicitly name the sibling tool as the inverse operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The idempotency behavior is documented, which implies safe repeated calls, but there's no explicit guidance on when to use this vs. alternatives like remove_pcg_node or connect_pcg_nodes. Usage context is implied by the clear purpose.

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