Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

set_state_linked_asset

DestructiveIdempotent

Convert a UStateTree state into a LinkedAsset state that points to another UStateTree, so it runs the target tree instead of local tasks.

Instructions

Turn a state into a LinkedAsset state pointing at another UStateTree (UStateTreeState::SetLinkedStateAsset). This forces the state's Type to EStateTreeStateType::LinkedAsset (the engine setter asserts on Type) and the setter clears Tasks, fixes the parameter layout from the linked subtree, and sets SelectionBehavior=TryEnterState — so a linked-asset state runs the target tree instead of local tasks.

Returns: { tree_path, state_name, state_type, linked_asset, set, saved }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tree_pathYesAsset path to the owning UStateTree.
state_nameYesName of the state to convert into a LinkedAsset state.
linked_asset_pathYesAsset path to the target UStateTree to link (must exist).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.0
    • changedInput schema / required
      Previous value: -[
-  "tree_path",
-  "linked_asset_path"
-]New value: +[
+  "tree_path",
+  "state_name",
+  "linked_asset_path"
+]
  2. First observedv1.1.0

TDQS

A4.1/5.0
Behavior5/5

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

Given annotations already declare destructiveHint=true and idempotentHint=true, this description goes well beyond them: it discloses that Type is force-set (the engine setter asserts on it), that Tasks are cleared, that the parameter layout is fixed from the linked subtree, and that SelectionBehavior is set to TryEnterState. These side-effects are exactly what an agent needs to know before a mutation.

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 primary action, then a compact side-effect clause, then the return shape. Slightly dense but every clause carries behavioral information that earns its place.

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?

Though there is no output schema, the description explicitly lists the return fields (tree_path, state_name, state_type, linked_asset, set, saved), and the annotations plus side-effect disclosure cover the mutation's risk profile. Adequate for a 3-param mutation tool.

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%, so all three parameters are already documented. The prose mentions the target subtree and owning tree concept but adds no syntax, format, or constraint details beyond the schema, so baseline 3 applies.

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 and resource: turn a state into a LinkedAsset state pointing at another UStateTree. It also names the underlying engine setter (UStateTreeState::SetLinkedStateAsset), which lets an agent distinguish it from siblings like set_state_type or set_state_selection_behavior.

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 description explains what the conversion does but never says when to prefer this over set_state_type or set_state_selection_behavior, nor any prerequisites (e.g. the target tree must exist). Usage is implied by the effect rather than explicitly routed.

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