Distributed Video QA MCP

Export a clip

video_clip

Cut a time range from a video into its own MP4 with audio, using instant stream copy or exact re-encoding for frame-accurate cuts.

Instructions

Cut a time range into its own MP4 with audio. Stream copy is instant; exact re-encodes.

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>",
      "start": "<start>",
      "end": "<end>"
    },
    "name": "video_clip"
  }
}

Input Schema

Name	Required	Description
`end`	Yes	Clip end in seconds.
`exact`	No	Re-encode for frame-accurate cuts; off snaps to keyframes.
`start`	Yes	Clip start in seconds.
`video_id`	Yes	Video id from video_list or an ingest result.
`output_dir`	No	Folder to write into (under DVQA_ALLOWED_ROOTS).

Output Schema

Name	Required	Description
`path`	Yes	The MP4 written.
`exact`	Yes	True when re-encoded for frame-accurate cuts.
`duration`	Yes	Seconds.
`has_audio`	Yes	Whether the clip has sound.
`size_bytes`	Yes	File size.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 13, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavior (the output is an MP4 that includes audio, and stream copy is fast while exact re-encodes), but it is silent on whether the call blocks or returns a job handle — a notable gap given the video_job/video_status siblings — and does not say the clip is written to disk.

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?

Two short sentences with zero filler, and the primary purpose is front-loaded ahead of the mode tradeoff. Nothing is repeated from the title or schema.

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?

With an output schema, full parameter coverage and annotations, the definition covers the essentials of what the tool produces and the speed/accuracy tradeoff. It is still thin on execution model (blocking vs job-based) and on the fact that it writes a file into an allowed root, both of which matter for correct invocation in this toolset.

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, but the sentence "Stream copy is instant; exact re-encodes" adds a performance dimension to the `exact` parameter that the schema's frame-accuracy wording does not convey. Other parameters (start, end, video_id, output_dir) are left entirely to the schema.

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?

"Cut a time range into its own MP4 with audio" gives a specific verb (cut/export) and resource (a clip file) plus the output format and audio inclusion. It is clearly distinct from siblings like video_download or video_frames, though it never names or contrasts with any of them explicitly.

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?

The description never states when to choose this tool over alternatives such as video_download, video_frames, or video_transcript, nor does it mention prerequisites (an ingested video_id) or whether the call is synchronous. The only guidance present is the internal tradeoff between stream copy and exact re-encode, which is mode selection rather than tool selection.

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