Skip to main content
Glama

Create a clip request

clipember_create_clip_request

Start a new AI clipping job from a YouTube (or direct video file) URL. Spends 1 credit — check clipember_get_credit_balance first if unsure. Returns immediately with a requestId; the pipeline (transcribe → score → crop → render) usually takes about 5 minutes, and about 1 run in 10 takes 15+ minutes. Call clipember_get_clip_request to check progress — don't poll more than once every 30-60 seconds, and expect to need a fresh call in a LATER turn/message rather than waiting synchronously in this one.

Input Schema

NameRequiredDescriptionDefault
endNoSeconds into the source to stop (max ~1200 = 20 min window)
urlYesYouTube URL or a direct video file URL
startNoSeconds into the source to start processing
seriesNoIf true, make a SERIES: one continuous story from the video split into 2-6 consecutive parts, each ending on a cliffhanger, with 'PART n/N' on screen. Schedule them in order with clipember_schedule_series once rendered.
teaserNoIf true, open each clip with a 1-3 second teaser of its payoff line before the clip starts (a cold open). Not applied to series parts.
languageNoSource language, ISO 639-1en
watermarkNoBurn a diagonal clipember.com watermark into the rendered clips. Omit to use the account setting (Settings → watermark); pass true/false to override it for this run.
noClippingNoIf true, render ONE clip of the whole [start,end] range instead of finding multiple highlights
preferredLengthNounder60sec

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds substantial non-derivable behavior: credit consumption, immediate return with a requestId, a ~5 minute typical pipeline with a 1-in-10 tail of 15+ minutes, and the anti-polling constraint. None of this is available from structured fields.

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 action and cost, then latency, then follow-up protocol. Every sentence carries operational information (cost, timing, tool routing, poll interval, turn boundary) with no filler.

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 an async job-creating tool with no output schema, it covers the essentials: what is charged, what is returned (requestId), how long it takes, and exactly how to retrieve results. An agent has everything needed to invoke it without guessing.

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 89%, so the schema already documents start, end, series, teaser, language, watermark, noClipping, and preferredLength in detail. The description only restates the 'url' source types, which the schema also states verbatim, so it adds little for the 9 parameters. Baseline 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?

States a specific verb and resource ('Start a new AI clipping job') plus the accepted input source forms ('YouTube (or direct video file) URL'). It is clearly distinguishable from siblings like clipember_get_clip_request, clipember_list_clip_requests, and clipember_schedule_series.

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?

Gives explicit preconditions (check clipember_get_credit_balance first, costs 1 credit), the correct follow-up tool (clipember_get_clip_request), a concrete polling cadence ('no more than once every 30-60 seconds'), and a workflow rule to continue in a later turn rather than blocking. This is when-and-how guidance an agent can act on directly.

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