Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

get_task_property

Read-onlyIdempotent

Read one property from a StateTree task node by reflection to inspect its C++ type, value, and has_value without modifying the asset.

Instructions

Read one property of a task node on a StateTree state by reflection, without changing the asset. Returns the value as JSON with its C++ type and has_value; only node struct properties are reachable, not instance data. Use get_task_info for the whole node and set_task_property to write.

Returns: { tree_path, state_name, task_index, property, type, value, has_value }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
propertyYesName of a property on the 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".
state_nameYesName of the state that owns the task; the command fails without it.
task_indexYes0-based index into the state Tasks, as listed by list_tasks.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.2.0
    • changedInput schema / properties / property / description
      Previous value: -"FProperty name."New value: +"Name of a property on the task node struct, e.g. \"FontScale\" on a debug text task; case-insensitive."
    • changedInput schema / properties / state_name / description
      Previous value: -"Name of the state."New value: +"Name of the state that owns the task; the command fails without it."
    • changedInput schema / properties / task_index / description
      Previous value: -"0-based index."New value: +"0-based index into the state Tasks, as listed by list_tasks."
    • changedInput schema / properties / tree_path / description
      Previous value: -"Asset path to the UStateTree."New value: +"Asset path of the StateTree, e.g. \"/Game/AI/ST_Guard\"."
    • changedInput schema / required
      Previous value: -[
-  "tree_path",
-  "task_index",
-  "property"
-]New value: +[
+  "tree_path",
+  "state_name",
+  "task_index",
+  "property"
+]
  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 already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuine value beyond that: the reflection-based read path, the no-mutation guarantee, the reachability limitation (node struct properties only, not instance data), and the JSON return shape with type and has_value.

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?

Two tightly written sentences front-load the operation and its scope limitation, followed by a compact return-shape line. Efficient, though the explicit 'Returns:' line partially duplicates fields implied elsewhere.

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, but the description supplies the return object shape (tree_path, state_name, task_index, property, type, value, has_value), the read-only guarantee, and the alternatives. An agent has enough to call it correctly; only minor depth is missing.

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% and all four parameters are documented in the schema (including the case-insensitive note for 'property' and the failure-without-state_name hint). The description adds no per-parameter syntax or format detail beyond the return field list, so the 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 (read one property of a task node on a StateTree state) and the mechanism (by reflection, without changing the asset). It also names the sibling tools it is adjacent to (get_task_info for the whole node, set_task_property to write), so an agent can distinguish it without opening schemas.

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?

Explicitly routes the agent: use get_task_info for the whole node and set_task_property to write. It also states a hard scope rule ('only node struct properties are reachable, not instance data'), which tells the agent when NOT to use it.

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