Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

set_evaluator_property

DestructiveIdempotent

Set a StateTree evaluator node property by reflection and save the asset, so AI agents can configure node struct values; instance data is not reachable.

Instructions

Write one property of a tree-scoped evaluator node of a StateTree asset by reflection and save the asset. Only node struct properties are reachable, not instance data. Returns value_changed, new_value and saved; the same value again gives value_changed false. Read it back with get_evaluator_property.

Returns: { tree_path, evaluator_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 evaluator node struct; case-insensitive.
tree_pathYesAsset path of the StateTree, e.g. "/Game/AI/ST_Guard".
evaluator_indexYes0-based index into the tree Evaluators, as listed by list_evaluators; out of range is an error.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.2.0
    • changedInput schema / properties / evaluator_index / description
      Previous value: -"0-based index."New value: +"0-based index into the tree Evaluators, as listed by list_evaluators; out of range is an error."
    • changedInput schema / properties / property / description
      Previous value: -"FProperty name."New value: +"Name of a property on the evaluator node struct; 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",
-  "evaluator_index",
-  "property"
-]New value: +[
+  "tree_path",
+  "evaluator_index",
+  "property",
+  "value"
+]
  2. First observedv1.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (non-readOnly, non-open-world, idempotent, destructive). Beyond that the description discloses persistence ('save the asset'), the idempotent outcome ('the same value again gives value_changed false'), and the reflection-based scope limit. It does not discuss permissions or side effects on dependent compilation, but it adds real context over the annotations.

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 core action and constraint, with no filler sentences. It is slightly redundant in listing the return fields twice (once in prose, once in the explicit return object), but that repetition is minor and the block is easy to scan.

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?

For a mutation tool with no output schema, the description supplies the return shape, the idempotency behavior, the scope limitation, and the read-back path, which covers what an agent needs. Only auth/compile-side-effect behavior is left implied, so it is complete but not exhaustive.

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 four parameters are already documented, including the JSON/FJsonObjectConverter semantics of value and the case-insensitivity of property. The description restates the node-struct restriction on property but adds no new syntax or format detail, so 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 verb+resource: writing one property of a tree-scoped evaluator node on a StateTree asset, by reflection, then saving. This is precise enough to separate it from the many other set_*_property siblings (task, condition, consideration, state) and it explicitly names its read counterpart get_evaluator_property.

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?

Provides the scope constraint 'Only node struct properties are reachable, not instance data' and points to get_evaluator_property for read-back, which is clear when-to-use context. It stops short of stating when not to use it against the sibling setters, so it is not a full routing rule.

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