Skip to main content
Glama

create_level_sequence

Destructive

Create and save a Level Sequence asset with a set duration and frame rate, or overwrite an existing one while migrating keys to the new rate.

Instructions

Creates a Level Sequence asset at package_path/sequence_name and saves it, with playback range [0, duration) and frame_rate, truncated to whole fps, as both tick resolution and display rate; the end frame is duration times that whole rate, to the nearest frame. If that asset already exists it is loaded and those settings are overwritten, its keys, sections and ranges migrated to the new rate so nothing moves in time; sequence_created tells a new asset from an existing one. Not undoable; another asset class at the path, or a duration shorter than one frame, is an error. To retime an existing sequence use set_sequence_frame_rate or set_sequence_duration; list sequences with get_level_sequences.

Returns: { sequence_name: string, package_path: string, duration: number, frame_rate: number, sequence_created: bool (false when the asset already existed), saved: bool, asset_path: string, playback_range_set: bool, tick_rate_set: bool, actual_start_frame: int, actual_end_frame: int }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
durationNoPlayback duration in seconds, above 0 and at most 3600, default 10
frame_rateNoFrame rate in fps, at least 1 and at most 120, truncated to whole fps, default 30
package_pathNoTarget content path, defaults to /Game/Sequences
sequence_nameYesName of the new sequence to create

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • changedInput schema / properties / frame_rate / description
      Previous value: -"Frame rate in fps, above 0 and at most 120, truncated to whole fps, default 30"New value: +"Frame rate in fps, at least 1 and at most 120, truncated to whole fps, default 30"
  2. Changed2 schema fields changedv1.2.0
    • changedInput schema / properties / duration / description
      Previous value: -"Playback duration in seconds, 0 to 3600, default 10"New value: +"Playback duration in seconds, above 0 and at most 3600, default 10"
    • changedInput schema / properties / frame_rate / description
      Previous value: -"Frame rate in fps, 0 to 120, default 30"New value: +"Frame rate in fps, above 0 and at most 120, truncated to whole fps, default 30"
  3. 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 declare destructive/non-idempotent/non-readOnly, and the description adds substantial context beyond them: the operation is not undoable, the overwrite path migrates keys/sections/ranges so nothing moves in time, and the sequence_created flag distinguishes new from existing assets. This is exactly the extra behavioral detail annotations cannot convey.

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-loads the core action and keeps routing, error conditions, and return shape compact; nearly every clause carries information the agent needs. The opening is a long run-on sentence and the trailing Returns block is dense, which costs it the top mark, but there is little true waste.

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 documents the full return shape (sequence_created, saved, actual_start_frame/actual_end_frame, etc.) plus the overwrite and error semantics for a complex creation-and-migration operation. Nothing an agent needs to call it correctly is missing.

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 beyond the per-param text: playback range is [0, duration), frame_rate is truncated to whole fps and used as both tick resolution and display rate, and the end frame is duration times that whole rate to the nearest frame. That elaboration of how duration and frame_rate interact earns above baseline.

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 ('Creates a Level Sequence asset at package_path/sequence_name') and immediately adds the scope details (playback range, frame rate handling) that separate it from the retiming siblings. An agent can distinguish this from set_sequence_frame_rate, set_sequence_duration and get_level_sequences 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 Guidelines5/5

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

Explicitly routes alternatives: 'To retime an existing sequence use set_sequence_frame_rate or set_sequence_duration; list sequences with get_level_sequences.' It also states when the tool is an error (another asset class at the path, duration shorter than one frame) and what happens on collision (existing asset is loaded and settings overwritten).

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