Distributed Video QA MCP

Read the transcript

video_transcript

Read-only

Retrieve timestamped spoken transcript lines for a whole video or a specific time range, in plain text, SRT, WebVTT, or JSON, with paging for long videos.

Instructions

What was said, for the whole video or a range: timestamped lines, plain text, SRT, WebVTT, or JSON segments. Page through long videos with start and end.

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_transcript"
  }
}

Input Schema

Name	Required	Description	Default
`end`	No	Up to this second.
`start`	No	From this second.
`format`	No	Output layout.	timestamped
`video_id`	Yes	Video id from video_list or an ingest result.
`max_chars`	No	Truncate beyond this.

Output Schema

Name	Required	Description
`note`	No	Why the output is empty or truncated.
`text`	No	Rendered transcript, for timestamped, plain, srt and vtt.
`title`	Yes	Its title.
`format`	Yes	The layout returned.
`language`	Yes	Spoken language.
`segments`	No	Raw segments, for json.
`video_id`	Yes	The video.
`truncated`	Yes	True when max_chars cut the output; page with start and end.
`segment_count`	Yes	Segments in the requested range.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 13, 2026

TDQS

A3.5/5.0

Behavior3/5

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 that long videos are paged via start/end and that several output layouts exist, but it never mentions truncation behavior (max_chars) or what happens when start/end fall outside the transcript — context the annotations don't supply.

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 with the core purpose front-loaded and the paging hint second. The opening phrase "What was said" is slightly informal but not wasteful; nothing superfluous is included.

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?

With an output schema present, the description needn't explain return values, and it covers the key behavioral aspects: format variants and range-based paging. Only the truncation semantics behind max_chars are left implicit, a minor gap for a read-only five-parameter tool.

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 every parameter including start, end, format, and max_chars is already documented. The description reinforces that start/end are paging controls and enumerates the format choices, but adds no syntax or edge-case meaning beyond the schema; baseline 3 applies.

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?

"What was said, for the whole video or a range" is a concrete verb-plus-resource statement, and the format list (timestamped, plain, SRT, WebVTT, JSON) further pins down what comes back. It is clearly a transcript-retrieval tool, though it never contrasts itself with sibling search tools like video_find_phrase.

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?

"Page through long videos with start and end" gives one clear usage pattern, so the agent can infer when range parameters matter. However, it offers no explicit when-to-use/when-not guidance versus other retrieval siblings, and no prerequisites or failure conditions.

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