Skip to main content
Glama

research_video

Retrieve a public video's title, channel, views, date, chapters, and official timestamped captions for research; report missing captions instead of inventing a transcript.

Instructions

Watch AND hear a public video: title, channel, views, date, chapters and the OFFICIAL caption track as a timestamped transcript.

The captions are the video's own track, so the audio is read without downloading a speech model. If a video has no captions, the tool says so instead of inventing a transcript (local transcription is a separate, explicit opt-in). Everything is read-only and public-page only.

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": {
      "url": "<url>"
    },
    "name": "research_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
max_linesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and does well: it declares read-only scope, public-page-only access, no media download or speech model involvement, and the exact behavior when captions are absent. It does not cover adjacent edge cases, such as private, deleted, or region-blocked videos, or whether very long transcripts are truncated by max_lines.

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?

It leads with the highest-value information, the returned fields, before explaining the caption mechanism, then closes with the safety scope. Three short paragraphs and no filler, though the aside about not needing to download a speech model is slightly more explanation than the agent strictly needs.

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 no output schema, the description must convey returned fields, and it does so explicitly. For a two-parameter read tool with no annotations it is largely sufficient, with the remaining shortfall being the unexplained max_lines semantics and any note on how malformed or non-public URLs are handled.

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

Parameters2/5

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

Schema description coverage is 0%, so neither url nor max_lines is documented in the schema, and the description adds no meaning for either. max_lines in particular (default 40) is left entirely unexplained, forcing the agent to guess that it caps transcript lines. The url parameter is at least inferable from 'public video', but the truncation behavior is a genuine gap the description should have closed.

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 a concrete verb (watch/read) and resource (a public video), and enumerates the returned artifacts: title, channel, views, date, chapters, and a timestamped caption transcript. That is far more specific than the tool name alone, though it never names a sibling such as research_youtube_search to mark the boundary between searching and fetching a single video.

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

Usage Guidelines4/5

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

It states the precondition (the video must be public) and the fallback path for the main failure mode: if no caption track exists, the tool reports that rather than fabricating a transcript, and local transcription is called out as a separate explicit opt-in. It stops short of naming the alternative tool or describing when to prefer a search tool over this one, so the guidance is clear but not exhaustive.

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