Skip to main content
Glama

add_subsequence_track

Nest one Level Sequence inside another by adding a subsequence track and a timed section, loading or creating the inner sequence and saving the target.

Instructions

Nests one Level Sequence in another: finds the target's first root track of exactly the subsequence class (never a cinematic shot track or another subclass) or adds one, adds a sub section playing the inner sequence from start_frame for duration tick-resolution frames, and saves the target. The inner sequence is sub_sequence_path, or _Sub in the target's folder when omitted; it is loaded when it exists, else created and saved as a new asset (inner_sequence_created says which). Each call adds another section. An inner sequence that cannot be loaded, created or saved (a new one that fails to save stays in memory only), that is the target itself, or that already plays the target at any depth is an error and nothing is added. success is false, with save_error, when the save of the target fails. For cinematic shots use add_shot_track.

Returns: { sequence_path: string, track_class: string, track_added: bool, section_added: bool, inner_sequence_created: bool (true only when this call created the inner sequence), start_frame: int, duration: int, section_count: int, sub_sequence_path: string, sub_sequence_name: string, saved: bool, save_error?: string }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
durationNoSection duration in tick frames (default 150).
start_frameNoInclusive start frame for the sub section (default 0).
sequence_nameNoAlias for sequence_path.
sequence_pathNoFull /Game path (e.g. "/Game/MyGame/SUBSEQ_Example") OR bare asset name of the target Level Sequence.
sub_sequence_pathNoOptional content path of the sub Level Sequence to nest. If omitted, a sibling inner Level Sequence is created and persisted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • removedInput schema / required
      Removed value: -[
      -  "sequence_path",
      -  "sequence_name"
      -]
  2. 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 only declare the safety profile (readOnly=false, destructive=false, idempotent=false), but the description adds substantial context beyond it: it saves the target, creates/saves a new inner asset when needed, leaves a failed-to-save new sequence in memory only, adds a new section on every call (reinforcing non-idempotence), and reports success=false with save_error on save failure.

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?

The primary action is front-loaded and every clause carries information (defaults, creation semantics, error cases, return fields), but it is a dense run-on paragraph with several stacked clauses. It is information-dense rather than padded, so it earns a 4 rather than lower.

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?

There is no output schema, yet the description embeds a full 'Returns' structure (sequence_path, track/section flags, inner_sequence_created, start_frame, duration, section_count, saved, save_error) and covers error and partial-failure behavior. Given no output schema, this is complete for the agent to call and interpret results.

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 already 100%, so the baseline is 3, but the description adds real meaning: the default sub_sequence_path is '<target name>_Sub in the target's folder', and start_frame/duration are described as inclusive start and tick-resolution duration. It does not clarify sequence_name vs sequence_path beyond the schema's 'Alias' note.

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 states a specific verb+resource (nests one Level Sequence in another by adding a subsequence track/section) and precisely scopes what track it targets ('first root track of exactly the subsequence class, never a cinematic shot track or another subclass'). It explicitly contrasts with the sibling add_shot_track, so an agent can distinguish it 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?

It names the alternative and the condition that selects it ('For cinematic shots use add_shot_track') and explains when the inner sequence is loaded vs created. It also enumerates error conditions (unloadable/uncreatable inner sequence, self-reference, cyclic play) that tell the agent when the call will fail, leaving little to inference.

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