Skip to main content
Glama
KyaniteLabs

kinocut

by KyaniteLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

video_auto_chapters

Detect scene changes in a video and generate chapter timestamps with descriptions, so viewers can navigate content by natural section breaks.

Instructions

Auto-detect scene changes and create chapters.

Analyzes video for scene cuts and returns chapter timestamps.

Args: input_path: Absolute path to input video. threshold: Scene detection threshold 0-1. Default 0.3.

Returns: List of (timestamp, description) chapter tuples.

Input Schema

NameRequiredDescriptionDefault
overwriteNoExplicitly allow replacing existing media. Existing non-media files are protected.
thresholdNo
input_pathYes

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. Addedv1.5.1

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full disclosure burden. It says nothing about whether files are written on disk, why an 'overwrite' parameter exists (contradicting the implication that this is a pure analysis returning tuples), or cost/runtime characteristics for long videos.

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, then a structured Args/Returns block; nothing is bloated. The first two sentences are near-duplicates of each other, and the Returns section restates what the output schema already declares.

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

Completeness2/5

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

With no annotations and an ambiguous read-vs-write profile, the description leaves the key operational question (does this produce files or only in-memory tuples, and what does overwrite do?) unresolved. The output schema already covers return shape, so the Returns paragraph adds little that was needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, and the description compensates for two of three params: input_path must be an absolute path, and threshold is a 0-1 scale defaulting to 0.3. The third param, overwrite, which is the behaviorally important one, is never mentioned in the description despite controlling whether existing media can be replaced.

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?

States a specific verb and resource: 'Auto-detect scene changes and create chapters', reinforced by 'Analyzes video for scene cuts and returns chapter timestamps'. However, it never names or contrasts with obvious siblings like video_detect_scenes or video_ai_scene_detect, so the agent must infer whether 'chapters' is the distinguishing output.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no prerequisites, and no mention of alternatives, despite at least two sibling tools (video_detect_scenes, video_ai_scene_detect) that overlap heavily with scene detection. The agent is left to guess which detector to pick.

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