Skip to main content
Glama

profile_blueprint_execution

Destructive

Statically analyze a Blueprint's structure and heuristic complexity, not runtime execution; use compile_for_timing=false for a read-only check that avoids recompiling or dirtying the asset.

Instructions

STATIC complexity analysis of a blueprint (node/function/variable counts + heuristic score). It does NOT profile any runtime execution. WARNING, SIDE EFFECT: by default it RECOMPILES the Blueprint purely to time the compile, which marks the asset dirty and can surface new compile errors on an asset you only meant to READ -- pass compile_for_timing=false for a genuinely read-only analysis. Three response fields are misnamed and each is flagged as such in the payload: execution_time is the COMPILE time in ms, cpu_usage is the heuristic complexity score (not CPU), and memory_usage is the .uasset size on disk (not memory).

Returns: { blueprint_path: string, resolved_object_path: string, blueprint_class: string, execution_time: number, memory_usage: int, cpu_usage: number, performance_rating: string, profile_status: string, total_nodes: int, function_count: int, event_count: int, variable_count: int, component_count: int, complexity_score: number, memory_score_mb: number, compilation_score_ms: number, blueprint_compiled: bool, is_static_analysis: bool, runtime_profiled: bool, recompiled_blueprint: bool, execution_time_is_compile_time_ms: bool, cpu_usage_is_complexity_score: bool, memory_usage_is_disk_file_size_bytes: bool, under_readonly_root: bool, side_effects: [string], recommendations?: [string] }

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.
blueprint_nameNoAlias of `blueprint_path` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `blueprint_path`.
blueprint_pathNoObject path, package path, or bare short name of the blueprint (resolved via mcp_common::ResolveAssetFlexible; ambiguity errors out listing candidates)
compile_for_timingNoOptional (default true): recompile the Blueprint to measure compile time. Pass false for a pure read-only analysis (execution_time/compilation_score_ms then report 0).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Discloses behaviors far beyond the annotations: the default recompile is a real side effect (marks asset dirty, can surface new compile errors on a read), the PIE interaction can kill the editor, and it proactively flags three misnamed response fields and what they actually mean. This aligns with destructiveHint=true and readOnlyHint=false rather than contradicting them.

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 the static/runtime distinction and the side-effect warning before the return list, and every clause is substantive (misnamed fields, PIE kill risk, dirty-asset consequence). It is long, but the density is justified and nothing is filler.

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 high-complexity tool with no output schema and real destructive side effects, the description supplies the return-field semantics, the PIE restriction, and the default-vs-read-only tradeoff. An agent has everything needed to call it correctly and safely.

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 meaning beyond the schema by tying compile_for_timing to its consequence (recompile marks dirty / reports 0 timing when false) and explaining why the alias blueprint_name exists. It goes past restating the schema descriptions.

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 precise verb+resource ('STATIC complexity analysis of a blueprint') and immediately disambiguates from the thing it is most likely to be confused with ('It does NOT profile any runtime execution'). An agent can distinguish it from runtime-profiling or compile_blueprint siblings 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 Guidelines4/5

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

Gives explicit conditional guidance: pass compile_for_timing=false for a genuinely read-only analysis, and the PIE-refusal rule is spelled out in the force parameter. However, it never names an alternative sibling tool (e.g. audit_blueprint_health, lint_blueprint_graph) for when a pure static check without recompile is wanted, so routing is implied rather than explicit.

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