Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

add_consideration

Idempotent

Attach a utility-AI consideration to a UStateTree state's Considerations array so utility-driven selection can rank children by score.

Instructions

Attach a utility-AI consideration (any struct deriving from FStateTreeConsiderationBase) to a state's Considerations array on a UStateTree. Considerations rank selectable children by score (0..1) when the state's selection behavior is utility-driven (e.g. TrySelectChildrenWithHighestUtility). Friendlier aliases are accepted in addition to the full struct name: "Constant" -> StateTreeConstantConsideration, "FloatInput"/"Float Input" -> StateTreeFloatInputConsideration, "EnumInput"/"Enum Input" -> StateTreeEnumInputConsideration. Use set_consideration_property to set initial values like Constant.Constant or FloatInput.Input. Idempotent: re-adding the same struct-type appends another consideration (engine semantics; considerations of the same type are valid).

Returns: { tree_path, state_name, consideration_class, consideration_count, added, saved }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tree_pathYesAsset path of the UStateTree
state_nameYesName of the state to attach the consideration to
consideration_classYesStruct name (FStateTreeConstantConsideration / StateTreeConstantConsideration) or alias (Constant|FloatInput|Enum Input|...)

Schema Changelog

Changes observed during successful MCP inspections.

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

TDQS

A3.9/5.0
Behavior2/5

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

The description adds useful behavioral context the annotations do not: alias resolution, the set_consideration_property follow-up, and the return shape. However, it says re-adding the same struct-type 'appends another consideration' while the annotations declare idempotentHint=true — repeated calls clearly produce additional effects, contradicting the annotation.

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-loads the core action and target, then layers on the utility-scoring rationale, aliases, follow-up tool, and idempotency note. Every sentence is relevant, though the idempotency sentence is wordy and internally muddled.

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 covers the target asset, aliasing, the value-setting companion tool, and the return payload, which is sufficient for correct invocation. Failure modes (e.g., unknown state_name or invalid class) remain unstated.

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 schema already documents the three parameters and even mirrors some alias examples. The description still adds value by giving the full explicit alias-to-struct mapping (Constant, FloatInput, EnumInput) and clarifying that both FStateTree* and StateTree* spellings are accepted.

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 (Attach) and resource (utility-AI consideration), plus the exact target (a state's Considerations array on a UStateTree). It is instantly distinguishable from siblings like set_consideration_property, remove_consideration, and list_considerations.

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?

Explains the context in which considerations matter (utility-driven selection such as TrySelectChildrenWithHighestUtility) and routes the agent to set_consideration_property for initial values. It stops short of an explicit when-not-to-use statement, but the alternative's role is named.

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