Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

add_state_tree_global_task_property

Set a property value on an existing global task within a StateTree asset and save it. Only node struct properties are reachable, not instance data.

Instructions

Write one property of an existing global task of a StateTree asset by reflection and save the asset; despite the name it adds nothing (create the task with add_state_tree_global_task). Only node struct properties are reachable, not instance data. Returns value_changed, new_value and saved.

Returns: { tree_path, global_task_index, property, set, value_changed, saved }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
valueYesNew value as JSON: a number, bool or string, or an object for a struct property, applied through FJsonObjectConverter.
propertyYesName of a property on the global task node struct, e.g. "FontScale" on a debug text task; case-insensitive.
tree_pathYesAsset path of the StateTree, e.g. "/Game/AI/ST_Guard".
global_task_indexYes0-based index into the tree GlobalTasks, as listed by list_global_tasks; out of range is an error.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.2.0
    • changedInput schema / properties / global_task_index / description
      Previous value: -"0-based index into ED->GlobalTasks."New value: +"0-based index into the tree GlobalTasks, as listed by list_global_tasks; out of range is an error."
    • changedInput schema / properties / property / description
      Previous value: -"FProperty name on the global task struct."New value: +"Name of a property on the global task node struct, e.g. \"FontScale\" on a debug text task; case-insensitive."
    • changedInput schema / properties / tree_path / description
      Previous value: -"Asset path."New value: +"Asset path of the StateTree, e.g. \"/Game/AI/ST_Guard\"."
    • addedInput schema / properties / value / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "integer"
+  },
+  {
+    "type": "boolean"
+  },
+  {
+    "type": "array"
+  },
+  {
+    "additionalProperties": true,
+    "type": "object"
+  }
+]
    • changedInput schema / properties / value / description
      Previous value: -"JSON value to apply."New value: +"New value as JSON: a number, bool or string, or an object for a struct property, applied through FJsonObjectConverter."
    • removedInput schema / properties / value / type
      Removed value: -"string"
    • changedInput schema / required
      Previous value: -[
-  "tree_path",
-  "global_task_index",
-  "property"
-]New value: +[
+  "tree_path",
+  "global_task_index",
+  "property",
+  "value"
+]
  2. First observedv1.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare the mutation profile (not read-only, not idempotent, non-destructive). The description adds beyond that: it saves the asset as a side effect, is implemented via reflection, and only node struct properties are reachable (instance data is not). The save-on-write side effect is the most valuable disclosure.

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 actual behavior and the name caveat before the return summary. Every clause carries information; the explicit Returns line is warranted since no output schema exists, though it slightly overlaps the tree_path/index/property arguments.

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?

No output schema exists, and the description compensates by listing the returned fields. With annotations covering mutation and the schema covering all four parameters, the only gap is that it does not describe failure modes beyond the schema's out-of-range note.

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. The description contributes real semantics on top: the 'property' argument is constrained to node struct properties reachable by reflection, excluding instance data, which the schema does not say.

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 precise verb+resource: write one property of an existing global task on a StateTree asset. It also pre-empts confusion from the misleading 'add' prefix by clarifying that it adds nothing, and names the sibling that actually creates tasks.

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

Usage Guidelines4/5

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

Explicitly routes the agent away from this tool for creation ('create the task with add_state_tree_global_task'), which is a genuine when-not. It does not, however, contrast against sibling setters like set_task_property, so an agent must infer which setter applies.

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