Skip to main content
Glama

Make an edited clip

edit_video

Make an edited copy of part of a public video (up to 60 s between start and end): vertical 9:16 or square crop, burned-in captions of the speech and of other sounds such as "[dog barking]" (in the language spoken, or translated to English, Portuguese, Spanish), even loudness; with a prompt also AI-written text over the picture (thought bubbles, meme captions, a title), a dramatic zoom, and slow motion or speed-up. Describe the edit in prompt, or set frame and captions_language (these override the prompt). Returns a gimmeclip.com/w/… watch link kept for 30 days; if it returns an edit_id, call edit_video again with only that edit_id to keep waiting. Each new edit counts against the caller's 30 edits a day, and preparing the source against the daily download limit; repeating the same edit is free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "edit_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoOptional: end of the part to keep, in seconds (after start).
urlNoLink to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo).
itemNoWhich video of a multi-video post (1-based); see get_video_info.
frameNo"9:16" vertical (default), "1:1" square or "original".
startNoOptional: start of the part to keep, in seconds.
promptNoOptional: the edit in plain words, e.g. "15-second vertical with Portuguese captions".
edit_idNoOnly to resume: edit_id from an earlier edit_video call that was still working.
captions_languageNoBurn in captions: "source" in the language spoken, or translated. Omit for no captions (unless the prompt asks for them).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Rich disclosure beyond annotations: the 60 s cap, the 30-day lifetime of the returned watch link, the edit_id resume protocol, and per-day quota/caching behavior. However, it does not flag that this is a long-running/blocking operation with real cost until the quota sentence, and readOnlyHint=false plus openWorldHint=true already signal a mutating external call. Adds real value but leaves polling/blocking semantics implicit.

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 and dense with no filler, but the opening is a single sprawling sentence that stacks crop, captions, loudness, prompt overlays, zoom and speed into one clause chain. Splitting the edit-capability list from the return-value/resume information would improve scannability. Nothing is redundant.

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?

Covers what matters for a complex, costly, open-world edit tool: output artifact, retention, resume flow, and rate limits. With no output schema, it correctly explains the return value. Missing an explicit statement of whether the call blocks or returns while still working (only implied by "if it returns an edit_id... keep waiting").

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 baseline is 3; the description goes beyond it by explaining the prompt vs frame/captions_language override relationship and the 60 s span between start and end. It also clarifies that edit_id alone resumes rather than re-editing. Remaining parameter meaning (item, url sources) is left entirely to the schema.

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+resource: "Make an edited copy of part of a public video," then enumerates the edit capabilities (crop, burned-in captions, loudness, prompt-driven overlays, zoom, speed). Clearly differentiated from download/get_transcript/get_video_info siblings by the editing outcome and the returned gimmeclip.com watch link.

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?

Explains how to invoke ("Describe the edit in prompt, or set frame and captions_language"), states the precedence rule (frame/captions_language override the prompt), and gives an explicit resume path (call again with only edit_id). Quota notes (30 edits/day, repeats free, source prep counts against download limit) help the agent decide whether to retry. No explicit when-not-to-use guidance or direction to pick a sibling instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources