Distributed Video QA MCP

Describe one video

video_info

Read-only

Retrieve a video’s source, dimensions, language, index counts, completed processing stages, and uploader description by ID to verify ingestion and QA readiness.

Instructions

Source, dimensions, language, index counts, completed stages and the uploader's description.

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_info"
  }
}

Input Schema

Name	Required	Description	Default
`video_id`	Yes	Video id from video_list or an ingest result.

Output Schema

Name	Required	Description
`id`	Yes	Video id used by every other tool.
`fps`	Yes	Frame rate.
`path`	No	Media file the server reads from.
`title`	Yes	Title from the site, or the file name.
`width`	Yes	Frame width in pixels.
`counts`	Yes	What is indexed for this video.
`height`	Yes	Frame height in pixels.
`length`	Yes	Length as m:ss or h:mm:ss.
`source`	Yes	The URL or path it was ingested from.
`status`	Yes	Only `ready` videos are fully searchable.
`duration`	Yes	Length in seconds.
`language`	No	Detected or given spoken language.
`uploader`	No	Channel or uploader, for URLs.
`has_audio`	Yes	Whether the media has a sound track.
`description`	No	Uploader's description, truncated to 2,000 characters.
`frame_count`	No	Indexed frames (in listings).
`source_kind`	Yes	Where it came from.
`stages_done`	Yes	Completed stages that a re-ingest will reuse.
`upload_date`	No	YYYYMMDD, for URLs.
`webpage_url`	No	Canonical page URL, for URLs.
`passage_count`	No	Retrieval passages (in listings).
`segment_count`	No	Transcript segments (in listings).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 13, 2026

TDQS

C2.5/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds nothing beyond that — no statement of what happens with an unknown or unprocessed video_id, no indication of whether this triggers processing, and it merely enumerates fields rather than behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

It is short with no wasted words, but it is an unstructured fragment lacking a subject or verb, so it is not front-loaded with purpose. Brevity here comes at the cost of clarity rather than from efficiency.

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?

An output schema exists, so the field list is largely redundant with structured data and the description should instead explain the retrieval action and its context. For a simple single-parameter read tool the bar is low, but the definition still leaves the core action and any failure conditions unstated.

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 100% and the single video_id parameter is already documented in the schema as coming "from video_list or an ingest result." The description adds no further meaning about the identifier, so the baseline 3 applies.

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

Purpose3/5

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

The description is a bare noun list ("Source, dimensions, language, index counts, completed stages and the uploader's description") with no verb or resource statement, so the action must be inferred from the tool name and title. It does tell an agent roughly what metadata is available, but it never says it retrieves metadata for a single video, and it does nothing to distinguish it from siblings like video_probe or video_status.

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 any alternative tool. An agent has to guess whether this is the right call versus video_probe, video_status, or video_list based on names alone.

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