Skip to main content
Glama

export_level_section

Destructive

Export actors from a loaded level, outliner folder, or whole world to JSON or TXT with name, class, and transform. Use it to inspect or back up level sections.

Instructions

Exports the actors of one section of the editor world (name, class, transform) to JSON or TXT. A section is a loaded level (the persistent level or a streaming sub-level, by package name), else an outliner folder (with its subfolders); '*' exports the whole world. An unknown section is an error that lists the loaded levels.

Returns: { section_name: string, export_format: string, export_success: bool, export_message: string, export_file_path: string, export_file_name: string, export_file_size_bytes: int, export_file_size_mb: number, level_name: string, world_name: string, section_scope: string ('world' | 'level' | 'folder'), actor_count: int, export_timestamp: string, export_status: string, export_directory: string }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
section_nameYesLevel package name (e.g. 'L_City_Interiors'), outliner folder path (e.g. 'Lighting' or 'Props/Trees'), or '*' for the whole world.
export_formatYesExport format: 'json' or 'txt'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this is a mutating/writing operation. The description implies file output via the export_file_path/export_directory return fields but never states that a file is written to disk, whether an existing file is overwritten, or where it lands — the most important behavioral detail for a destructive-hint tool.

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 purpose and section semantics in the first two sentences, followed by the return contract. The inline return-field enumeration is long, but it is justified because there is no output schema, so it earns its space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description supplies the full return shape, plus section resolution and error behavior, which is the bulk of what an agent needs. It is only short of complete on filesystem behavior (target directory, overwrite semantics).

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% and both parameters are documented there, but the description adds real meaning beyond the schema: the resolution precedence (level first, then folder), the inclusion of subfolders, and the error contract listing loaded levels. That is more than baseline when the schema already does the field-level work.

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+scope: exports the actors (name, class, transform) of one section of the editor world to JSON or TXT. The meaning of 'section' is defined, so the agent can distinguish this from the many other export_* siblings without opening a 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?

Explains the conditional resolution of section_name (loaded level by package name, otherwise outliner folder with subfolders) and that '*' exports the whole world, plus error behavior for unknown sections. It gives clear context for how to call it but names no alternative tool or when-not-to-use condition.

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