Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

get_blueprint_exec_path

Read-onlyIdempotent

Read which Blueprint nodes and branches actually ran at runtime from the debugger trace stack. Use it to verify if a silent graph path executed.

Instructions

Report which exec nodes and BRANCHES actually RAN inside a Blueprint at runtime -- which Branch went true, which FunctionResult fired -- read from the editor's Blueprint-debugger trace stack. Unlike trace_blueprint_execution and profile_blueprint_execution, which are STATIC and list every node that exists, this reflects real execution, so it answers "did that path run at all?" when a graph fails silently. WARNING: two-phase by construction: the VM only records the trace for the object currently being DEBUGGED, so call it ONCE with object_path to arm recording (SetObjectBeingDebugged), then drive the PIE scenario, then call it AGAIN to read the recorded path -- a single call returns nothing and that is not a bug. Requires a running PIE session with Blueprint debugging; world (including 'server' / 'client' / 'pie:N') selects which instance gets armed, and the response stamps which world it was.

Returns: { blueprint_name, blueprint_path, debug_object_set, object_path, trace_stack_size, filtered_count, path:[{index, node_id, node_class, node_title, graph, function, context, is_branch, is_function_result, observation_time}], note, world_selector, world_name, world_package, world_type, net_mode, pie_instance (the world of the ARMED debug object; nulls when none was armed) }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
worldNoWorld to resolve object_path in: absent/'editor' (default) | 'server' (the PIE world with authority) | 'client' | 'pie:N' | 'pie'/'game'/'runtime' (ambiguous). A fully-qualified PIE object path (...UEDPIE...) resolves regardless of this.
max_samplesNoMax trace-stack samples to scan (default 500).
object_pathNoOptional live PIE object to set as the debugged instance (arms trace recording).
function_nameNoOptional: only include samples in a function/graph whose name contains this.
blueprint_nameNoBlueprint / AnimBlueprint asset path or short name to filter the trace to.
blueprint_pathNoAlias of `blueprint_name` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `blueprint_name`.
set_debug_objectNoWhen object_path is given, call SetObjectBeingDebugged on it. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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, yet the description adds major load-bearing behavior: the two-phase arm-then-read protocol, the WARNING that a single call returns nothing and is not a bug, and the requirement for a running PIE session. This exactly exceeds what the annotations provide and prevents a very likely misuse.

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 purpose, then siblings, then the critical two-phase warning, then the return shape. Dense but every segment earns its place. The full return-structure listing pushes it somewhat long, but it remains structured and skimmable.

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?

For a 7-parameter, stateful, no-output-schema tool, the description supplies the runtime preconditions, the calling protocol, the world-selection behavior, and the full response shape. Nothing an agent needs to call this correctly (and avoid the null-result trap) 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 schema carries the parameter detail and a baseline of 3 is expected. The description goes beyond it by explaining the phase-role of object_path, the world selector semantics ('server'/'client'/'pie:N' and the ambiguity note), and the response-stamped world, adding cross-parameter meaning the schema doesn't.

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?

The description opens with a precise verb+resource+scope: it reports which exec nodes and branches actually RAN in a Blueprint at runtime, read from the debugger trace stack. It explicitly contrasts itself with the static siblings trace_blueprint_execution and profile_blueprint_execution, so an agent can distinguish it 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?

It gives an explicit when-to-use ("did that path run at all?" when a graph fails silently), names the two alternative tools, and states a hard precondition (a running PIE session with Blueprint debugging). The two-phase calling protocol is spelled out directly, and world-selection is described.

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