Skip to main content
Glama
KyaniteLabs

kinocut

by KyaniteLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

video_edit

Execute a full timeline-based edit from a JSON specification. Combine clips, audio, overlays, transitions, and export settings in a single operation.

Instructions

Execute a full timeline-based edit from a JSON specification.

The timeline JSON describes video clips, audio tracks, text overlays, image overlays, transitions, and export settings in a single operation.

Image overlays are applied in a single filtergraph pass (no multiple re-encodes).

Sequence shortcut (simple multi-clip chain with per-boundary transitions)::

{
  "clips": ["a.mp4", "b.mp4", "c.mp4"],
  "transitions": ["fade", "dissolve"],
  "transition_duration": 0.5
}

Args: timeline: Full Timeline JSON (width/height/tracks/export) or the sequence shortcut above. Can also be a JSON string or a path to a .json file. Image overlays in tracks: {"type": "image", "images": [{"source": "logo.png", "position": "top-right", "width": 200, "opacity": 0.8}]} output_path: Where to save the final video. Auto-generated if omitted.

Input Schema

NameRequiredDescriptionDefault
timelineYes
overwriteNoExplicitly allow replacing existing media. Existing non-media files are protected.
output_pathNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.16.4
    • addedInput schema / properties / overwrite
      Added value: +{
+  "default": false,
+  "description": "Explicitly allow replacing existing media. Existing non-media files are protected.",
+  "title": "Overwrite",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv1.16.0
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed3 schema fields changedv1.5.1
    • removedInput schema / properties / timeline / additionalProperties
      Removed value: -true
    • addedInput schema / properties / timeline / anyOf
      Added value: +[
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "type": "string"
+  }
+]
    • removedInput schema / properties / timeline / type
      Removed value: -"object"
  4. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

There are no annotations, so the description must carry the behavioral load, and it does deliver one meaningful trait: image overlays are 'applied in a single filtergraph pass (no multiple re-encodes),' which signals an efficiency/quality characteristic. It omits major behavioral facts for a heavy mutation tool — whether the whole timeline re-encodes, cost/runtime expectations, how errors or missing sources surface, and whether overwrite defaults to protecting files. Partial disclosure only.

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 purpose sentence is front-loaded and the examples earn their space by disambiguating the two accepted timeline forms. The JSON snippets are long but directly usable, and there is no filler prose. Slightly example-heavy for the prose budget.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the shortcut form and overlay structure are covered. However, the timeline parameter's schema is an opaque anyOf object with additionalProperties, meaning the description is the only source of truth for the full timeline grammar — and it only gestures at 'width/height/tracks/export' without enumerating track types or required keys. For a tool this complex with no annotations, that leaves a real gap.

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 33% (only overwrite has a schema description), but the description compensates well: it explains that timeline accepts full Timeline JSON or the sequence shortcut, and may also be a JSON string or a path to a .json file, and it shows the nested image-overlay object shape. output_path is documented as auto-generated when omitted. The compensation is strong, though the full timeline schema remains only loosely described.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Execute a full timeline-based edit from a JSON specification,' and then enumerates what the timeline covers (clips, audio, text, image overlays, transitions, export). That sets it apart from single-purpose siblings like video_trim or video_add_text by framing it as a full composition operation. It never names a sibling or states when to prefer this over them, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The description documents a sequence shortcut for the 'simple multi-clip chain with per-boundary transitions' case, which implies when the full timeline structure is unnecessary. It does not, however, say when to use video_edit versus composing with video_merge/video_composite_layers/video_overlay, nor what prerequisites (source files existing, validation) apply. Usage is implied rather than stated.

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