Unreal-MCP-Ghost

Overview Schema Source Related Servers Discussions Admin

skill_audit_blueprint_health

Audits Unreal Engine Blueprint health and returns a 0-100 score based on compile status, disconnected pins, unused variables, and reference count. Identifies issues to guide fixes.

Instructions

Audit the health of a Blueprint and return a structured report.

Calls only existing atomic tools (bp_get_graph_summary, bp_get_graph_detail, project_get_references, bp_compile). Does not use exec_python directly.

The audit checks: • Compilation status (had_errors flag) • Variable inventory • Disconnected exec pins (execution chains broken) • Disconnected non-exec input pins without defaults • Unused variables (declared but not referenced in any graph) • Incoming reference count

Returns a 0–100 health_score: 100 — clean compile, no issues 70-99 — minor issues (unused vars, unconnected data pins) 40-69 — significant issues (disconnected exec chains) 0-39 — compile failure or severe disconnection

Args: blueprint_name: Asset name (e.g. 'BP_HealthSystem'). blueprint_path: Full package path. None = '/Game/Blueprints/'. compile_check: Whether to run bp_compile. Default True.

Returns: JSON StructuredResult with outputs: compiles_clean, variable_count, function_graph_count, node_count_total, disconnected_exec_pins, disconnected_input_pins, unused_variables, incoming_references, warnings, health_score

KB: see knowledge_base/32_AGENT_PLAYABLE_SLICE_RECIPE.md#overview Example: skill_audit_blueprint_health(blueprint_name="/Game/MCP_Test/BP_Example")

Input Schema

TableJSON Schema

Name	Required	Description	Default
`compile_check`	No
`blueprint_name`	Yes
`blueprint_path`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 20, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations, the description carries the full transparency burden and does so thoroughly. It explicitly names the four atomic tools it uses, states that it does not use exec_python directly, breaks down the six audit categories, and documents the health_score scoring bands. This goes well beyond typical descriptions and gives an agent an accurate model of the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with labeled sections (audit checks, returns, args, KB, example) and no filler. It front-loads the purpose and method, then provides parameter details and an example, all in a scannable format.

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?

The description enumerates every output field of the StructuredResult, gives concrete health score thresholds, provides an example invocation, and links to a KB recipe. Even though no output schema is present, the agent gets enough information to use the tool correctly and interpret its results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description compensates completely. blueprint_name gets an example, blueprint_path gets its None-default resolution rule, and compile_check gets its meaning and default. Every parameter is individually explained with practical context.

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 'Audit the health of a Blueprint and return a structured report,' a specific verb+resource pairing that clearly identifies the tool's function. It further distinguishes itself from sibling blueprint tools by enumerating the exact checks it performs and stating it composes existing atomic tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives like bp_validate_blueprint, bp_find_disconnected_pins, or bp_validate_graph. The purpose is clear and the KB reference points to a recipe, but the conditions that make this composite audit preferable to individual checks are left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server