llms.ink

Frame of a video

video_frame

Read-onlyIdempotent

Get one frame of a video (YouTube, Instagram, X, TikTok, a direct .mp4 link…) as a JPEG image, to see what is on screen at a given time. Pair with llms_full_txt: the transcript is timestamped.

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": "video_frame"
  }
}

Input Schema

Name	Required	Description
`t`	No	Time in the video: seconds ("90", "90.5") or "1:30" / "1:02:03". Default "0".
`url`	Yes	The video link, e.g. "youtube.com/watch?v=…" or "instagram.com/reel/…". The scheme is optional.
`width`	No	Maximum width in pixels. Default 1280.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavior context: the return is a JPEG image and the tool reaches out to a broad set of third-party platforms. It does not mention failure modes for unsupported links or any size/time limits, which keeps it from a 5.

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 compact sentences, front-loaded with the verb and output format, followed by the platform list and the pairing hint. Nothing is redundant and no sentence could be dropped without losing information.

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?

For a simple three-parameter read tool with no output schema and full annotation coverage, the description supplies the essentials: output type, supported sources, and how to complement it with the transcript tool. Minor omission is any statement about behavior on unsupported URLs or media limits.

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 t, url and width are already documented in the schema with formats and defaults. The description only gestures at the time parameter via "at a given time" and adds no syntax or constraint detail beyond the schema. Baseline 3 is appropriate.

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 and resource ("Get one frame of a video ... as a JPEG image") plus the scope of supported sources (YouTube, Instagram, X, TikTok, direct .mp4) and the intent ("to see what is on screen at a given time"). An agent can distinguish this from the transcript siblings llms_full_txt/llms_txt 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 clear context for use ("to see what is on screen at a given time") and an explicit companion tool ("Pair with llms_full_txt: the transcript is timestamped"), which tells the agent how this fits with the alternative. It stops short of stating when not to use it, e.g. what to do when the source is unsupported.

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

All llms.ink tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?