Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

click_pie_widget

Destructive

Fires a live UMG widget's named event in a running Play-In-Editor session, triggering bound click handlers so UI flows can be tested headless.

Instructions

Fire a LIVE UMG widget's event in the running PIE session (game thread): resolve a UWidget by name among the active viewport UserWidgets (reusing the read_pie_widgets walk) and BROADCAST its named BlueprintAssignable multicast delegate (default OnClicked). Unlike read_pie_widgets (read-only) this MUTATES runtime state -- it runs the exact bound handlers a real click would, including the client->server RPC path, so equip/inventory/craft UI flows can be driven headless instead of by a human (driving them via call_function bypasses that RPC path and yields false negatives). Errors clearly if no Play-In-Editor session is running or the widget/event is not found.

Returns: { success: bool, widget_name, resolved_widget, resolved_class, event, is_bound: bool, fired: bool, player_index, child_name?, world: string, world_name: string|null, world_package: string|null, world_type: string|null, net_mode: string|null, pie_instance: number } -- is_bound is false when the delegate exists but has no bound handlers (broadcast is still a safe no-op).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
eventNoOptional (default "OnClicked"): BlueprintAssignable multicast delegate to fire (e.g. "OnClicked", "OnPressed", "OnReleased").
worldNoOptional world selector: absent/'pie' (default: PlayWorld, else the first PIE context) | 'server' (the PIE world with authority) | 'client' | 'pie:N' | 'game' (alias of 'pie'). In a 2-player PIE session EVERY client has its OWN widgets, so the default may well read the other player's HUD.
child_nameNoOptional: after resolving widget_name, drill into a descendant widget with this name (the resolved widget's own WidgetTree if it is a UserWidget, else a named child in its subtree) and fire the event on THAT widget instead.
widget_nameYesRequired. Name of the target UWidget in the live tree (as reported by read_pie_widgets), e.g. "ConfirmButton". Matches a widget inside an active viewport UserWidget's WidgetTree, or a top-level UserWidget by its own name.
player_indexNoOptional (default 0): when set, only consider viewport UserWidgets owned by the local player with this index (single-player PIE resolves globally).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, non-idempotent, non-readOnly, so safety is covered. The description still adds real context: it runs the exact bound handlers including the client->server RPC path, is_bound=false is a safe no-op, and it errors clearly when the session or widget/event is missing. Solid beyond-annotation disclosure.

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 the read_pie_widgets contrast before mechanics; dense but every clause carries information. Slightly long due to the inline return-field enumeration, but not wasteful.

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?

No output schema exists, yet the description enumerates the return fields and their semantics (is_bound, fired, resolved_class, world info, pie_instance), and annotations cover safety. An agent has everything needed to call and interpret it.

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 five params (event, world, child_name, widget_name, player_index) are already documented in the schema. The description restates the default event and hints at the 2-player ambiguity but adds little syntax the schema lacks. Baseline 3 applies.

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 (fire/broadcast a delegate) on a specific resource (a LIVE UMG widget in the running PIE session), and explicitly distinguishes itself from the read-only sibling read_pie_widgets in the same sentence. An agent can route to it without opening a 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 frames when to use it vs the read-only walk and vs call_function ('driving them via call_function bypasses that RPC path and yields false negatives'), and names the failure condition (no PIE session running). Strong when/when-not guidance.

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