Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

remove_blueprint_function

Destructive

Delete a function graph owned by a Blueprint by name, verifying the graph is removed from the Blueprint's FunctionGraphs list. Errors on unresolvable names or interface overrides.

Instructions

Delete a function graph OWNED BY the Blueprint (Blueprint->FunctionGraphs) by name. WARNING: It resolves more graphs than it can delete: name lookup goes through FindGraph (all graphs, interface overrides and macros included) but the delete only touches FunctionGraphs and only when bAllowDeletion is true, so an INTERFACE OVERRIDE resolves and cannot be removed. That case is a hard error naming the reason -- to change an interface override, author the signature on the INTERFACE and re-create it (add_function_parameter on the BPI_ -> compile_blueprint -> implement_interface_function). Not idempotent: a name that does not resolve is an error. TRAP when deleting to re-create: the class is NOT regenerated here, so an immediate add_blueprint_function with the same name fails with "is an inherited overridable function (declared on )" because the stale UFunction is still in the generated class -- put a compile_blueprint BETWEEN the two calls. Callers of the removed function are left broken until the next compile.

Returns: { blueprint_name: string, removed_function: string, success: bool } -- success:true means the graph is gone from Blueprint->FunctionGraphs (re-read after the delete), not merely that the call ran.

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.
function_nameYesName of the function graph to remove; must exist, be owned by this Blueprint and be deletable, or the call errors
blueprint_nameNoName of the blueprint
blueprint_pathNoAlias of `blueprint_name` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `blueprint_name`.

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 cover the safety profile (destructive, not idempotent), but the description adds far more: the FindGraph-vs-delete resolution mismatch, the hard error on interface overrides, the non-regeneration of the generated class, and the stale-UFunction trap. This is genuine behavioral context beyond annotations.

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?

Dense and front-loaded with the WARNING and TRAP clearly marked, but it is long and packs multiple concepts (ownership, interface overrides, recreate sequencing, caller breakage) into few sentences. Every clause earns its place, though it reads as a wall of text.

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 destructive tool with no output schema, it covers the full operational picture: ownership semantics, the interface-override failure mode, the recreate sequencing trap, non-idempotence, and the exact return shape including what success:true actually verifies.

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: it explains why blueprint_path exists (a sibling-spelling alias) and reinforces that function_name must exist, be owned, and be deletable. The force/PIE refusal is documented in the schema, not the description.

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+resource and precisely scopes it: 'Delete a function graph OWNED BY the Blueprint (Blueprint->FunctionGraphs) by name.' It even disambiguates against the broader FindGraph lookup, distinguishing it from its siblings like add_blueprint_function and compile_blueprint.

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?

Explicit when-this-works and when-it-fails guidance: interface overrides resolve but cannot be deleted, and it names the exact alternative workflow (add_function_parameter on the BPI_ -> compile_blueprint -> implement_interface_function). It also gives the exact sequencing rule for the delete-and-recreate trap.

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