Distributed Video QA MCP

Outline a video

video_chapters

Read-only

Extracts chapter markers with time spans, opening words, and keywords, using uploader chapters or detecting topic shifts in transcripts and silent-video frames.

Instructions

Chapters with spans, opening words and distinguishing keywords. Uses the uploader's chapters when the source has them; otherwise finds topic shifts in the transcript embeddings (frames for silent video).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "video_id": "<video_id>"
    },
    "name": "video_chapters"
  }
}

Input Schema

Name	Required	Description
`image_px`	No	Long side of chapter images.
`video_id`	Yes	Video id from video_list or an ingest result.
`include_images`	No	Attach one frame per chapter.

Output Schema

Name	Required	Description
`title`	Yes	Its title.
`chapters`	Yes	In time order.
`video_id`	Yes	The video.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 13, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds genuinely non-obvious behavior: uploader-provided chapters take precedence, otherwise topic shifts are found in transcript embeddings, with frame detection as the silent-video fallback. It does not mention cost/latency of embedding computation or whether results are cached, which would have made this a 5.

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?

Two compact sentences, no filler. The first sentence is telegraphic ('Chapters with spans, opening words and distinguishing keywords') and slightly clipped, but every clause carries information and the fallback logic is ordered correctly in the second sentence.

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

Completeness4/5

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

An output schema exists and the schema documents all three parameters, so the description need not explain returns. It covers provenance and the silent-video edge case. The remaining gap is minor: it doesn't state whether the video must already be ingested, despite video_id referring to 'an ingest result'.

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 description coverage is 100%, so video_id, include_images and image_px are already documented in the schema. The description adds nothing about the parameters, not even that include_images governs the per-chapter frame. Baseline 3 is appropriate when the schema does the heavy lifting.

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 names the resource (chapters) and enumerates its contents: spans, opening words, distinguishing keywords. It also states the two generation paths (uploader chapters vs. transcript embeddings), which lets an agent distinguish it from video_transcript or video_frames. It stops short of a clear leading verb like 'extract' or 'generate', but the purpose is unambiguous.

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?

Usage is only implied: an agent infers this tool is for outlining/skimming a video. There is no explicit 'use this when you want X instead of video_transcript' guidance and no named alternative, though the sibling list contains several plausible overlaps. The provenance note (uploader chapters preferred) helps but is behavioral, not routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.