Skip to main content
Glama

Video Description

video_description

Index what happens on screen in a video as timestamped events, scenes, and metadata by passing a video URL or file; use it for visual content, not audio speech.

Instructions

Describe what happens on screen in a video, as a timestamped index of events.

The visual counterpart of transcription: reads the picture, not the audio track (for speech use the transcription tools). Pass exactly one source: video_url for a YouTube, Twitter/X, Twitch, Kick or TikTok link, or video_file for a file.

The result is a JSON document: {"events": [{"start", "end", "description", ...}], "scenes": [...], "meta": {"duration", "preset", ...}}, with start/end in seconds. Priced on machine time, so longer videos and higher presets cost more; quote first with video_description_price. A long video can take several minutes: if the tool times out, follow up with check_job_status.

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": {
      "model": "<model>"
    },
    "name": "video_description"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesVideo description model (e.g., 'Marlin_2B')
presetNoDetail level: 'fast', 'balanced' or 'detail'. Higher presets read small on-screen text and logos but cost more (roughly x1 / x1.7 / x3.75 machine time). Unset: 'balanced', or the cheapest preset the model offers. Ignored by models without presets
video_urlNoLink to a video on YouTube, Twitter/X, Twitch, Kick or TikTok; the API fetches it itself. Not for a direct link to a video file: pass that as video_file. Live streams and audio-only sources (Twitter Spaces) are rejected
video_fileNoVideo file as a direct URL to the file (preferred), data URI (data:video/mp4;base64,...) or base64 string; this server uploads it. Must contain a video stream
webhook_urlNoHTTPS URL for deAPI to call when this job finishes. Notifies your own systems; the tool still returns the result here
webhook_secretNo32-255 char key deAPI signs the callback with (HMAC-SHA256). Needs webhook_url. A secret given in chat stays in the transcript
include_metadataNoReturn the source's title, channel, upload date and view/like counts. URL sources only; carries a flat surcharge
return_result_in_responseNoReturn the description JSON inline in 'result'. Set to False for long videos to get only the download URL

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.3

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations at all, the description carries the full burden and does so: it discloses the cost model (machine time, longer videos and higher presets cost more), realistic latency ("can take several minutes"), the timeout recovery path, and the accepted source types with live-stream/audio-only rejections. These are the exact behaviors an agent needs before committing to a slow, paid job.

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 core purpose, then source rules, then output shape, then cost/latency caveats in a sensible order. The inline JSON sketch is compact and useful rather than padding, though the paragraph runs long for an 8-parameter tool and could be split more sharply.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a long-running, paid, multi-source generation tool with no annotations, the definition covers what the output looks like, how cost accrues, how to recover from a timeout, and how to choose the source parameter. An output schema exists, so the return-value detail is bonus rather than required, and nothing an agent needs to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline would be 3, but the description adds a real constraint the schema never states: "Pass exactly one source" for video_url vs video_file, plus the platform list for URLs. It does not touch webhook_secret, include_metadata, or return_result_in_response beyond what the schema already documents.

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?

"Describe what happens on screen in a video, as a timestamped index of events" is a precise verb+resource+output shape, and the follow-up line explicitly positions it against the transcription siblings ("reads the picture, not the audio track"). An agent can pick this over video_url_transcription/video_file_transcription 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 Guidelines5/5

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

Names the alternatives (transcription tools) with the condition that selects them, states the exactly-one-source rule, points to video_description_price for quoting, and routes to check_job_status on timeout. This is explicit when/when-not/alternatives guidance.

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