Skip to main content
Glama

set_bp_variable_metadata

DestructiveIdempotent

Set editor-facing checkboxes and text on an existing Blueprint variable: instance editability, SaveGame serialization, SpawnActor exposure, category, and tooltip. Only supplied fields change.

Instructions

Set the editor-facing checkboxes and text of an existing Blueprint variable: instance_editable (per-instance editability), save_game (CPF_SaveGame -- whether the variable goes into a .sav), expose_on_spawn (adds the variable as a pin on SpawnActor), category and tooltip. Only the fields present are touched; passing none is an error. This is the fix for a variable created by add_blueprint_variable, which is born NOT instance-editable while the readers report it as editable. Variable must be declared on THIS Blueprint; on a library variable the answer is a child class of your own, not this call. WARNING: this call does NOT compile: it structurally-modifies the Blueprint, which regenerates the SKELETON only, so a save_game just written is authored but NOT yet on the generated class the save archive reads -- the response says so in save_game_needs_compile, and the loop that finishes the job is compile_blueprint -> save_asset -> get_blueprint_variable_detailed_info and check save_game_generated.

Returns: { blueprint_name, variable_name, updated, save_game?, save_game_generated?, save_game_needs_compile? } -- updated:true only means at least one field was applied, not that it persisted. The three save_game_* fields appear only when save_game was passed, and are READ BACK after the write: save_game off the variable descriptor, save_game_generated off the FProperty of the generated class.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
forceNoOptional. This command is REFUSED while a Play-in-Editor session is running: it either compiles a Blueprint (the reinstancer can retain a world, and CheckForWorldGCLeaks is Fatal -- it KILLS the editor) or writes to disk (Editor.AllowSavingAssetsDuringPIE=0 makes the engine refuse the write, so it would report success without writing a byte). Stop PIE and retry instead; force=true runs it anyway, at your own risk.
tooltipNoTooltip text shown for the variable
categoryNoCategory to group the variable under in the editor
save_gameNotrue = tick "SaveGame" (CPF_SaveGame), so a SaveGame archive (ArIsSaveGame) serializes this variable; false unticks it. The only headless way to set this flag -- set_property_value, Python, set_bp_variable_replication and BlueprintEditorLibrary all refuse it. Needs a compile to reach the generated class.
variable_nameYesName of a variable declared on THIS Blueprint (inherited ones are refused).
blueprint_nameNoBlueprint name or path.
blueprint_pathNoAlias of `blueprint_name` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `blueprint_name`.
expose_on_spawnNotrue = the variable shows up as an input pin on SpawnActorFromClass. Verify on the NODE's pins, not on get_blueprint_variables' expose_on_spawn, which reports false for variables that ARE exposed.
instance_editableNotrue = editable on each placed actor. Verify by WRITING the placed instance and reading it back; the reporting field is unreliable for every variable.

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 declare destructive/idempotent/write hints, but the description adds pivotal context they cannot: that the call structurally modifies the Blueprint and regenerates the SKELETON only, that save_game is authored but not yet on the generated class, that updated:true does not mean persisted, and the corrective compile loop. This is exactly the beyond-annotations disclosure the bar rewards.

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?

Purpose is front-loaded in the first sentence, followed by field list, usage rule, and a clearly demarcated WARNING and Returns block. Dense but every segment carries operational information; it is slightly verbose against what an agent strictly needs to invoke the call.

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 9-param mutation tool with no output schema, the description supplies the return shape (blueprint_name, variable_name, updated, and conditional save_game_* fields), the read-back provenance of each, and the compile loop needed to persist. Nothing material to correct invocation is left out.

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, but the description adds real meaning: 'Only the fields present are touched; passing none is an error', that save_game is the only headless way to set the flag, and the read-back semantics of the three save_game_* fields. These clarify inter-parameter behavior rather than restating types.

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 and resource ('Set the editor-facing checkboxes and text of an existing Blueprint variable') and enumerates the exact fields touched. It also situates itself against siblings by naming add_blueprint_variable as the source of the problem it fixes and implying distinction from readers like get_blueprint_variable_detailed_info.

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?

Gives explicit when-to-use ('This is the fix for a variable created by add_blueprint_variable, which is born NOT instance-editable'), when-not ('Variable must be declared on THIS Blueprint; on a library variable the answer is a child class of your own, not this call'), and the follow-up sequence (compile_blueprint -> save_asset -> get_blueprint_variable_detailed_info).

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