Skip to main content
Glama
WeftCut

WeftCut

by WeftCut
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

add_video_layer

Add a video or image layer to a track with specified source and timeline points; automatically pairs linked audio on the same track's audio lane.

Instructions

Add a visual layer from an imported Video or Image item onto a track and return its record; an audio-only item is refused and pointed at add_audio_layer. Video: src_in_us/src_out_us are the source in/out points, t_start_us/t_end_us the timeline span. Image: an ImageOverlay over the timeline range; omit src_in_us/src_out_us. When a Video has an audio stream and auto_pair_audio_on_import is on (the default), a linked dialogue Audio layer lands on the SAME track's audio lane, committed atomically — an occupied lane rejects the whole call naming the blocker. The record always carries audio_layer_id/link_id/audio (null when unpaired).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
media_idYesMedia id.
t_end_usYesTimeline end (exclusive), µs.
track_idYesTrack id.
src_in_usNoSource in point, µs. Required for Video; ignored for an Image.
src_out_usNoSource out point (exclusive), µs. Required for Video; ignored for an Image.
t_start_usYesTimeline start, µs.
composition_idNoOptional cross-check: the composition `track_id` belongs to; refused on mismatch. The track alone fixes the composition.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv0.1.9
    • changedInput schema / properties / composition_id / description
      Previous value: -"Optional cross-check: the composition `track_id` must belong to (a Group's id from `project://compositions`). The track alone fixes the composition; omit unless you want the mismatch refused."New value: +"Optional cross-check: the composition `track_id` belongs to; refused on mismatch. The track alone fixes the composition."
    • changedInput schema / properties / composition_id / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • addedInput schema / properties / media_id / description
      Added value: +"Media id."
    • addedInput schema / properties / src_in_us / description
      Added value: +"Source in point, µs. Required for Video; ignored for an Image."
    • addedInput schema / properties / src_out_us / description
      Added value: +"Source out point (exclusive), µs. Required for Video; ignored for an Image."
    • addedInput schema / properties / t_end_us / description
      Added value: +"Timeline end (exclusive), µs."
    • addedInput schema / properties / t_start_us / description
      Added value: +"Timeline start, µs."
    • addedInput schema / properties / track_id / description
      Added value: +"Track id."
    • changedInput schema / required
      Previous value: -[
-  "media_id",
-  "src_in_us",
-  "src_out_us",
-  "t_end_us",
-  "t_start_us",
-  "track_id"
-]New value: +[
+  "media_id",
+  "t_end_us",
+  "t_start_us",
+  "track_id"
+]
  2. First observedv0.1.8

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the single destructiveHint=false annotation, the description adds substantial behavioral context: audio-only items are refused, auto-paired audio layers are created atomically, an occupied lane rejects the whole call, and the returned record always contains specific fields. These are critical runtime behaviors an agent needs to anticipate, and none of them contradict 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence earns its place. It is front-loaded with the core purpose, then organizes conditional behavior clearly (Video vs Image, audio pairing), and ends with the return-record guarantee. Despite its length, there is no filler and the structure aids scanning.

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 tool with 7 parameters and no output schema, the description covers the important return fields, conditional parameter usage, audio-pairing side effects, and failure behavior. It is complete enough for an agent to invoke the tool correctly without needing to guess at undocumented behavior.

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. The description adds genuine value beyond the schema by explaining how src_in_us/src_out_us apply to Video, that they must be omitted for Image, and how t_start_us/t_end_us map to the timeline range. It also clarifies the compositional/atomic interaction between parameters, which the schema alone does not convey.

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 ('Add'), a specific resource ('imported Video or Image item'), and the target ('onto a track'), plus the action's outcome ('return its record'). It clearly distinguishes itself from a sibling by noting that audio-only items are refused and pointed at add_audio_layer, so an agent can immediately tell what this tool is for.

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?

The description explicitly tells when to use this tool ('from an imported Video or Image item') and when not to ('an audio-only item is refused and pointed at add_audio_layer'). It also gives conditional usage guidance for Video vs Image parameters, which fully resolves the main routing decision among relevant siblings.

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