Skip to main content
Glama

screenshots

Capture still frames from a YouTube video at specified timestamps to inspect slides, code, diagrams, or people on screen without downloading the full video.

Instructions

Grab still frames from a YouTube video at the given timestamps.

Use this to see what is on screen (slides, code, diagrams, people) at specific moments. Combine with get_transcript or transcribe for the surrounding speech. Only the frames are fetched, not the whole video.

Args: url: YouTube URL or video ID. times: Timestamps to capture, e.g. ["17:11", "19:21"]. Max 10. max_height: Maximum frame height in pixels (default 720).

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>",
      "times": "<times>"
    },
    "name": "screenshots"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
timesYes
max_heightNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations supplied, the description does real work: it discloses that only frames are extracted rather than the whole video (a cost/scope signal) and caps timestamps at 10 per call. It does not mention auth, quota, latency, or the form the frames are returned in, which leaves some behavioral gaps for a no-annotation tool.

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?

Front-loaded with the action and the visual-vs-speech distinction, then a compact Args block. The Args block is justified because the underlying schema has zero descriptions, though a few phrases ("Combine with...") could be tightened.

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?

For a 3-param tool with no annotations and no output schema, the description covers inputs well but never explains what comes back (image payloads, URLs, one frame per timestamp?). The frame-extraction and 10-timestamp limit help, but return-shape ambiguity is a real gap when no output schema exists.

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

Parameters5/5

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

Schema coverage is 0%, so the description carries all param meaning, and it does: `url` accepts either a YouTube URL or a bare video ID, `times` takes timestamp strings with a concrete example ("17:11") plus a max of 10 that appears nowhere in the schema, and `max_height` is explained as a pixel cap with its 720 default.

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

Purpose5/5

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

States a specific verb+resource ("Grab still frames from a YouTube video") and scopes it to timestamps. It explicitly contrasts itself with `get_transcript`/`transcribe` (speech) versus frames (visual), so an agent can pick correctly without opening any schema.

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?

Gives concrete when-to-use cases ("slides, code, diagrams, people") and recommends combining with `get_transcript` or `transcribe` for the surrounding speech. It lacks an explicit when-not rule (e.g., use `video_info` for metadata only), but the usage context is unmistakable.

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