Skip to main content
Glama

OpenShorts.io

Clip a video into Shorts

clip_video

Submit one YouTube, TikTok, Instagram or Facebook video. OpenShorts picks the strongest moments, crops them to 9:16 and burns in captions. Uses the account's minutes (source length). Returns a job id; processing usually takes 10–20 minutes, so call get_job later to collect the clips.

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": "clip_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesLink to a single public video: YouTube (watch, shorts, youtu.be), TikTok, an Instagram reel or post, or a Facebook video or reel.
caption_styleNoCaption look: default (Big uppercase, coral active word); hormozi (Words appear as they are spoken); pill (Solid box behind the active word); lime (Bright green active word box); oneword (One big word at a time); clean (Sentence case, soft shadow). Default: default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does well: it discloses the asynchronous job model, a 10–20 minute processing estimate, and a billing model ('uses the account's minutes (source length)'). It omits failure modes, length/format limits, and what happens when minutes are exhausted.

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 short sentences, front-loaded with the action, then the processing behavior, then the return value and next step. No redundant restatement of the title and nothing that could be cut.

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 two-parameter async tool with no output schema, the description covers everything needed to call it correctly: accepted input type, cost model, latency, the job id return, and the get_job handoff. Remaining gaps are edge-case behavior, not invocation essentials.

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% and the url field already enumerates accepted link formats, so the schema does the heavy lifting. The description adds only the constraint that it must be a single public video and the note that minutes are charged by source length; caption_style 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?

Names a specific verb and resource ('Submit one YouTube, TikTok, Instagram or Facebook video') and states the transformation the service performs: picks the strongest moments, crops to 9:16, burns captions. An agent can tell this apart from get_job/list_jobs/get_usage because the description frames itself as the intake step that produces a job id.

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?

Gives clear when-to-use context (one public video from a supported platform) and explicitly routes follow-up behavior to get_job rather than implying this call returns results. It does not state when NOT to use it or what preconditions exist (e.g., no remaining minutes), so it falls just short of the 5 bar.

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