Skip to main content
Glama

watch_video

Extract timestamped video frames and the matching transcript for a chosen time range. Use even or scene-based sampling to inspect slides, demos, and on-screen details.

Instructions

'Watch' a video: returns frames (images, each labelled with timestamp) plus the transcript for the same range. mode='even' spaces frames evenly; mode='scenes' samples twice as many moments and keeps the ones that differ most (best for slides, demos, edited videos). Use start/end ('90', '1:30') to zoom in and call again for detail. n_frames max 24 (default 6); width 512 saves tokens, raise to ~768 only to read small on-screen text (or use ocr_frames).

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": "watch_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
urlYes
langNoauto
modeNoeven
startNo
widthNo
n_framesNo
include_transcriptNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations supplied, the description carries the behavioral burden and does well: it discloses the return shape (images labelled with timestamps + transcript), the hard cap n_frames max 24, the token cost tradeoff of width, and the fact that detail requires iterative zoomed re-calls. It does not cover failure behavior, video-length limits, or what happens when no transcript is available.

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?

Front-loaded with the core purpose, then the mode choice, then the zoom workflow, then the cost knobs — a sensible priority order. Every clause carries actionable content; nothing is redundant filler.

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?

No output schema exists, so the description correctly spends its words describing the return payload and token economics for an 8-parameter tool. It is nearly complete for correct invocation; only the undocumented lang parameter and unaddressed failure/length limits keep it from a 5.

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 0% across 8 params, yet the description supplies real meaning for mode, start/end (with accepted formats '90' and '1:30'), n_frames (max 24, default 6), width (512 token-saving default, ~768 ceiling), and implicitly include_transcript. The gap is lang, whose accepted values and 'auto' behavior by default are undocumented anywhere.

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?

'Watch' a video is stated as a specific verb+resource, and the description immediately defines what comes back: timestamped frames plus the transcript for the same range. It also carves out a distinction from the sibling ocr_frames for the small-text case, so an agent can route without opening a 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?

Explicit selection guidance is given for the mode enum ('even' spaces evenly; 'scenes' keeps the most-differing moments and is 'best for slides, demos, edited videos'). It also gives a concrete workflow rule — use start/end to zoom in and call again for detail — and a token decision rule (512 default, ~768 only for small on-screen text, or use ocr_frames instead).

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