Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

get_task_info

Read-onlyIdempotent

Read a task's class, instance ID, and properties from a named state in a StateTree asset without changes. Use list_tasks to find task indices.

Instructions

Read one task of a named state in a StateTree asset without changing it: the task node's struct name (class), its instance_id and every property of the node struct as JSON (properties). The task's instance data is not included. Errors when the tree, its editor data or the state is missing, or task_index is out of range; state_name picks the first state with that name. List a state's tasks with list_tasks; read or write one field with get_task_property or set_task_property; global tasks: list_global_tasks.

Returns: { tree_path, state_name, task_index, class, instance_id, properties: {...} }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tree_pathYesAsset path to the UStateTree.
state_nameYesName of the state.
task_indexYes0-based index into State->Tasks.

Schema Changelog

Changes observed during successful MCP inspections.

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

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare read-only/idempotent/non-destructive, but the description adds substance on top: explicit error conditions (missing tree, editor data, state, or out-of-range task_index), the state_name first-match resolution rule, and the exclusion of instance data. This is behavior an agent needs that structured fields don't supply.

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 purpose, then behavior, then sibling routing, then the return shape. Dense but each clause carries information; the only minor cost is that the return-shape line could arguably move to an output schema, though none exists.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description supplies the return shape itself ({ tree_path, state_name, task_index, class, instance_id, properties }), plus error conditions and boundaries. Nothing needed to call it correctly is missing.

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 goes beyond the schema by explaining state_name's disambiguation behavior (picks the first state with that name) and the error raised for an out-of-range task_index, adding real semantic meaning for two of the three parameters.

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 (Read), a precise resource (one task of a named state in a StateTree asset), and its scope ('without changing it'). It also names what is and isn't returned (class, instance_id, properties; instance data excluded), so an agent can distinguish it from any sibling without opening the schema.

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 to alternatives: list_tasks to list a state's tasks, get_task_property/set_task_property for single-field read/write, and list_global_tasks for global tasks. It also defines when state_name is ambiguous (first match wins), removing inference.

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