Skip to main content
Glama
Sign In

ClipFlux

by ai.clipflux
OverviewDiscussionsAdmin

Write a video script

draft_video

If you have not yet in this chat, call get_started first. Starts a ClipFlux video. Without a script, ClipFlux writes the script from the topic, then stops so the user can read and change it before anything is drawn. With a script, ClipFlux uses those exact words and only plans the pictures: a Short, or a long video whose minutes come from the script and whose # lines become chapters. Writing or planning the script uses a few credits (about 2 to 3); nothing is drawn and nothing else is charged until make_video, and its card shows the price and the user's credits on the Make button, so call it as soon as the look and narrator are chosen and there is a first version of the script (no quote_video first). Its card is the ClipFlux script box, where the user edits the lines; do not paste the script in your reply. An account with a free preview (quote_video says so) gets the opening of the video made for free instead, with no script step. The ClipFlux card shows the result: do not add pictures, searches or a card of your own.

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": {
      "title": "<title>",
      "topic": "<topic>",
      "format": "<format>"
    },
    "name": "draft_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
lookNoA look id from list_looks, or "own:..." for one of the user's saved own looks. Default: the account default.
titleYesThe video's title as a viewer would read it, short (for example "Why the Titanic sank so fast"). No length, format or style words.
topicYesThe angle and the points to cover, in plain sentences. Not instructions about the format: the format, length and look are their own fields.
voiceNoA narrator id from list_voices. Default: the look default.
formatYes"long" for a 16:9 YouTube video in chapters, "short" for a vertical Short.
pacingNoLong videos only: "standard" or "fast". Default standard.
scriptNoThe narration word for word, written with the user under the script rules from get_started (only the spoken words: no labels, timings or notes; for a long video, chapter titles as lines that start with #). A Short takes up to 2,000 characters. ClipFlux speaks exactly this text. Leave it out to let ClipFlux write the script.
likeUrlNo"Make one like this": a video link already read with read_youtube_link (for a channel, its best video's link). The draft follows that video's format (hook, structure, pacing, ending), never its words; its look and narrator are the defaults unless you pass look or voice. The topic is still yours: one of the read's angles, or the same topic in new words.
minutesNoLong videos ClipFlux writes: the length in minutes. Default 10. Leave it out with a script: the script sets the length.

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 say it is a non-read-only, non-destructive, closed-world call; the description adds the credit cost (about 2 to 3), the fact that nothing is drawn and nothing else is charged until make_video, that the price and balance appear on the Make button, and that the result surfaces in the ClipFlux script card. It also tells the agent not to paste the script into its reply, which is behavior no annotation could convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The prerequisite is correctly front-loaded and no sentence is pure filler, but several sentences are run-ons that bundle four or five separate facts (the credits sentence chains cost, deferral, card pricing and call timing). It is dense rather than tight, which costs readability for an agent parsing it once.

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 9-parameter creation tool with no output schema, it covers cost, deferral of charges, what the user sees, the free-preview exception, the editing surface, and the follow-up tool (make_video). Nothing an agent needs in order to call it correctly and set expectations is missing.

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 on top: the script/minutes interaction ("Leave it out with a script: the script sets the length"), the # line convention becoming chapters, and how likeUrl borrows format but never words. It does not restate the per-field defaults, which is fine since the schema already does.

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?

The description names a specific verb and resource ("Starts a ClipFlux video") and immediately splits the two modes of operation: without a script it writes one and stops; with a script it uses the exact words and only plans pictures. That is enough to distinguish it from make_video, quote_video and edit_draft without opening any schema.

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?

It states explicit prerequisites ("call get_started first"), an explicit timing rule ("call it as soon as the look and narrator are chosen and there is a first version of the script"), and an explicit exclusion ("no quote_video first"). It also carves out the free-preview case where "there is no script step", so the agent knows when this tool is not the right one.

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

All ClipFlux toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources