Skip to main content
Glama

video_extract_frame

Destructive

Extract a single video frame as an image; specify a timestamp for an exact moment or omit it to auto-pick a thumbnail (first frame at timestamp 0).

Instructions

Extract one frame as an image. Without a timestamp, picks a smart thumbnail (fallback: 10% into the clip); pass 0 for the first frame.

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": {
      "input_path": "<input_path>"
    },
    "name": "video_extract_frame"
  }
}

Input Schema

NameRequiredDescriptionDefault
overwriteNoAllow replacing existing media files.
timestampNoExplicit time in seconds, or None for automatic sampling.
input_pathYesAbsolute path to the video.
output_pathNoWhere to save the frame. Auto-generated if omitted.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv2.0.0
    • addedInput schema / properties / input_path / description
      Added value: +"Absolute path to the video."
    • removedInput schema / properties / input_path / title
      Removed value: -"Input Path"
    • addedInput schema / properties / output_path / description
      Added value: +"Where to save the frame. Auto-generated if omitted."
    • removedInput schema / properties / output_path / title
      Removed value: -"Output Path"
    • changedInput schema / properties / overwrite / description
      Previous value: -"Explicitly allow replacing existing media. Existing non-media files are protected."New value: +"Allow replacing existing media files."
    • removedInput schema / properties / overwrite / title
      Removed value: -"Overwrite"
    • addedInput schema / properties / timestamp / description
      Added value: +"Explicit time in seconds, or None for automatic sampling."
    • removedInput schema / properties / timestamp / title
      Removed value: -"Timestamp"
    • removedInput schema / title
      Removed value: -"video_extract_frameArguments"
    • removedOutput schema / title
      Removed value: -"video_extract_frameDictOutput"
  2. Changed1 schema field changedv1.16.4
    • addedInput schema / properties / overwrite
      Added value: +{
      +  "default": false,
      +  "description": "Explicitly allow replacing existing media. Existing non-media files are protected.",
      +  "title": "Overwrite",
      +  "type": "boolean"
      +}
  3. Changed4 schema fields changedv1.16.0
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / timestamp / anyOf
      Added value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / timestamp / default
      Previous value: -0New value: +null
    • removedInput schema / properties / timestamp / type
      Removed value: -"number"
  4. Addedv1.5.1

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotence, and the description never mentions that an existing file may be replaced or that a file is written at all. What it does add beyond structured fields is genuinely useful and non-obvious: the 'smart thumbnail' heuristic with a 10%-into-clip fallback, which an agent could not predict from the schema.

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 with the core action front-loaded and the conditional behavior following. Every clause carries information; nothing is repeated from the schema or annotations.

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 an output schema present, return values need no explanation, and all four parameters are documented in the schema. The description covers the one genuinely ambiguous input (timestamp) well; the only gap is any acknowledgement of the destructive write/overwrite behavior flagged in annotations.

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 is 3, but the description adds real meaning for 'timestamp' beyond the schema's 'None for automatic sampling' by spelling out the actual heuristic (smart thumbnail, 10% fallback) and the special value 0 for the first frame. It does not touch overwrite or output_path, but those are fully documented in the schema.

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 opens with a specific verb and resource ('Extract one frame as an image'), which cleanly separates it from siblings like video_trim, video_info, or video_merge. It does not explicitly name or contrast an alternative tool, so it stops short of a 5.

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

Usage Guidelines3/5

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

The guidance is about how to call the tool (omit timestamp for auto-sampling, pass 0 for the first frame) rather than when to choose it over a sibling such as video_info or video_shorts. A user can infer the use case is grabbing a still/thumbnail, but no explicit when-to-use or when-not-to-use statement is given.

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