Skip to main content
Glama

Cut a YouTube video

cut_youtube_video

Cut YouTube video clips by time range and get a direct download URL. Submit start/end times, choose format and resolution, and receive the produced link.

Instructions

Cut a clip (or clips) from a YouTube video and return its download URL. Submits a cut job to AppsGolem and (by default) polls until it's produced, then returns the produced status — which includes a download_url once a download token is ready. Pricing: 1 credit per produced clip (4K = 4/clip, except audio_only which stays 1; a known source duration > 2h adds +1 once); a batch/stitch of N clips costs N per-clip. Failed cuts are never billed. On a wait-timeout the result has still_processing=true; poll get_cut_status with the returned id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNoClip end as "SS"/"MM:SS"/"HH:MM:SS" (≤300h). Omit when passing clips.
urlYesA YouTube video URL (watch/share/youtu.be — playlists rejected).
fastNoStream-copy (≈10× faster, keyframe-aligned); video/nosound/both only. Mutually exclusive with a non-1× speed — fast wins and speed is forced to 1.0.
modeNoOne of "video" (video file, default; MP4 normally, source container e.g. WebM in fast mode), "audio_only" (mp3/m4a/wav/flac), "both" (video + MP3 zip), "nosound" (video, no audio), "short" (portrait 9:16; AI smart-crop when applicable, else letterbox-blur with source-dependent aspect), "gif" (animated GIF, ≤5 min), "frames" (JPG stills).video
waitNoPoll until ready (default) up to the timeout_seconds polling deadline.
clipsNoA non-empty list of 1–10 {start,end} ranges INSTEAD of start/end.
sheetNoFrames — a single contact-sheet JPG (2..80 frames, single clip); disables burn_ts.
speedNoPlayback speed 0.5/1.0/1.25/1.5/2.0; video/nosound/both/audio_only.
startNoClip start as "SS"/"MM:SS"/"HH:MM:SS" (≤300h). Omit when passing clips.
stitchNoWith 2+ clips, join them into one file (else a zip of clips); ignored for a single clip; video/audio_only/both/short/nosound only.
bitrateNoLossy-audio bitrate "320"(default)/"256"/"192"/"128" — MP3/M4A in audio_only, MP3 in both; ignored for wav/flac.
burn_tsNoFrames — burn the source timestamp onto each JPG.
resolutionNo144p/240p/360p/480p/720p/1080p (default)/1440p/2160p (4K; total cut ≤60 min).1080p
interval_msNoFrames sampling interval — 100/500/1000/2000(default)/5000/10000; non-sheet extraction is capped at 1800 JPGs total across all clips.
audio_formatNoaudio_only output format — "mp3"(default)/"m4a"/"wav"/"flac". both always produces MP3.
idempotency_keyNoA stable key (≤200 chars) so a retried request reuses the same job.
timeout_secondsNoPolling deadline in seconds when wait=true (default 300); submission + one in-flight status request can extend total wall-clock.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed21 schema fields changedv0.1.2
    • removedInput schema / properties / audio_format / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / audio_format / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / bitrate / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / bitrate / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / burn_ts / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / burn_ts / type
      Added value: +[
      +  "boolean",
      +  "null"
      +]
    • changedInput schema / properties / clips / anyOf
      Previous value: -[
      -  {
      -    "items": {
      -      "properties": {
      -        "end": {
      -          "anyOf": [
      -            {
      -              "type": "string"
      -            },
      -            {
      -              "type": "null"
      -            }
      -          ]
      -        },
      -        "start": {
      -          "anyOf": [
      -            {
      -              "type": "string"
      -            },
      -            {
      -              "type": "null"
      -            }
      -          ]
      -        }
      -      },
      -      "type": "object"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "properties": {
      +        "end": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "start": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / end / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / end / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / fast / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / fast / type
      Added value: +[
      +  "boolean",
      +  "null"
      +]
    • removedInput schema / properties / idempotency_key / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / idempotency_key / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / sheet / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / sheet / type
      Added value: +[
      +  "boolean",
      +  "null"
      +]
    • removedInput schema / properties / speed / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / speed / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedInput schema / properties / start / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / start / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / stitch / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / stitch / type
      Added value: +[
      +  "boolean",
      +  "null"
      +]
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations present, the description carries the full burden and does so thoroughly: it discloses asynchronous job submission, default polling, wait-timeout semantics (still_processing=true), the need to poll get_cut_status with the returned id, and detailed billing rules including no charge on failure. This is far more transparent than a simple 'cuts a video' statement.

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?

Three tightly packed sentences deliver purpose, process, return value, pricing, and timeout behavior with no filler. Every sentence earns its place and the most important information is front-loaded.

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?

Despite 17 parameters and no output schema, the description covers all operational essentials: what is returned, how the async job behaves, what to do on timeout, and cost/failure semantics. The fully-covered schema handles parameter-level details, so nothing critical is missing for correct invocation.

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 all 17 parameters are already documented in detail. The description adds operational context around job lifecycle and pricing but does not add per-parameter meaning beyond what the schema states, so the baseline score of 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?

Opens with a specific verb and resource: 'Cut a clip (or clips) from a YouTube video and return its download URL.' This clearly distinguishes it from siblings get_cut_status (polling job status) and get_account_balance (billing). The additional detail about submitting a cut job and returning produced status refines rather than obscures the core purpose.

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?

Provides clear context: the tool submits a cut job, polls by default, and explicitly directs the agent to get_cut_status when a wait-timeout occurs. It does not fully enumerate when to avoid this tool or mention get_account_balance, but the key alternative behavior is explicitly covered.

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