Skip to main content
Glama

compile_blueprint

Destructive

Compile a Blueprint to regenerate its class and verify zero errors before other nodes call it. Returns real compile status, error/warning counts, and node-anchored messages.

Instructions

Compile a Blueprint to regenerate its class, returning the REAL outcome (succeeded == zero errors) plus the error/warning counts, and with return_messages=true the per-message log with each message anchored to its node_id/graph. Required after authoring functions, variables or RPCs and before anything calls them. TRAP: num_errors:0 is not a promise the graph works -- an unresolved WILDCARD pin on an array/ForEach node can compile clean and still block PIE, and warnings (a "was pruned" node whose consumers silently read defaults) do not lower it. Read the warnings too, and get_compile_errors as a second opinion.

Returns: { name: string, compiled: bool, succeeded: bool, num_errors: int, num_warnings: int } -- compiled/succeeded reflect the ACTUAL compile outcome (true iff zero errors; warnings still compile). Both the default and return_messages paths return these fields. When return_messages=true additionally { messages: [{severity: 'error'|'warning'|'note', text: string, node_id: string, node_title: string, graph_name: string}] } (node_id/node_title/graph_name are empty strings when the message is not anchored to a graph node)

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_nameNoName of the blueprint. A short name matching two assets compiles ONE of them silently -- pass the full path when in doubt.
blueprint_pathNoAlias of `blueprint_name` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `blueprint_name`.
return_messagesNoOptional (default false). When true, ALSO returns the per-message compiler results log so callers can see node-anchored errors/warnings. When false/absent the response omits the `messages` array but still reports the REAL compile status.

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?

Annotations only cover the safety profile (destructiveHint=true), and the description adds substantial behavioral context beyond that: warnings do not lower num_errors, pruned-node consumers silently read defaults, and the full response shape is spelled out since there is no output schema. Nothing contradicts the 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?

Front-loaded with the compile action and the TRAP warning before the return-shape detail, and each sentence carries information. Minor redundancy: the compiled/succeeded explanation is stated twice ('returning the REAL outcome (succeeded == zero errors)' and again in the Returns block).

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?

With no output schema, the description fully documents the default and return_messages response shapes, and annotations already carry the safety profile. An agent has everything needed to call it correctly and interpret the result.

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 four parameters (force, blueprint_name, blueprint_path, return_messages) are already documented in the schema, including the PIE-refusal nuance for force. The description repeats the return_messages behavior without adding syntax beyond the schema, so the 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+resource ('Compile a Blueprint to regenerate its class') and immediately distinguishes its role from siblings by naming get_compile_errors as a second opinion. The description of what the return values mean (compiled/succeeded true iff zero errors) goes beyond the name.

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 states when it is required ('after authoring functions, variables or RPCs and before anything calls them'), when the normal result is misleading (the num_errors:0 / WILDCARD pin TRAP), and which sibling to consult for a second opinion. This is the textbook when/when-not/alternative structure.

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