ClipFlux

Create a channel

create_channel

Creates a ClipFlux channel: its name, niche, what it is about, Long or Shorts, how often it should post, and optionally its look and narrator. Free. Autopilot starts OFF; set_autopilot switches it on after the user agrees. Built from a channel read with read_youtube_link: pass its channel link as referenceUrl, and write a NEW name and an angle of its own, never a copy.

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": {
      "name": "<name>",
      "niche": "<niche>",
      "about": "<about>",
      "format": "<format>",
      "cadence": "<cadence>"
    },
    "name": "create_channel"
  }
}

Input Schema

Name	Required	Description
`look`	No	A look id from list_looks.
`name`	Yes	The channel name (the user's choice).
`about`	Yes	What the channel is about and for whom, a few sentences.
`niche`	Yes	The niche in a few words.
`voice`	No	A narrator id from list_voices.
`format`	Yes
`cadence`	Yes	weekly = once a week, twice = twice a week, daily = every day.
`referenceUrl`	No	The https://www.youtube.com/channel/UC... link read_youtube_link returned, when it is built from that channel.
`referenceName`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already establish this is a non-destructive, non-read-only, closed-world write, so the description's added value is real: it discloses that creation is free (no credit spend), that autopilot defaults to OFF on creation, and that a reference-derived channel must not be a verbatim copy. It does not say what happens on name collisions, validation failures, or whether cadence can later be changed here.

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?

The purpose is front-loaded in one sentence and the remaining three sentences each carry distinct operational information (cost, autopilot default, reference workflow). The telegraphic fragments ("Free.", "Long or Shorts") cost some readability but no sentence is filler.

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?

For a nine-parameter creation tool with no output schema, the definition covers purpose, triggers, cost, and the key post-creation step well. The remaining gaps are that it never indicates what the call returns (channel id, link, handle) needed to chain into set_autopilot or draft_video, and referenceName is left undefined.

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 coverage is 78%, so the structured fields already do most of the work, and much of the description's parameter content (referenceUrl as the read_youtube_link output, name being a new choice) restates or lightly reinforces that. The one genuinely undocumented parameter, referenceName, receives no explanation in either schema or description, and format/cadence semantics are only implied in prose.

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?

"Creates a ClipFlux channel" names a specific verb and resource, then enumerates exactly which attributes define the channel (name, niche, about, format, cadence, optional look/narrator). An agent can immediately distinguish this from read-only siblings like list_channels or get_started without opening the 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?

Explicit sequencing and alternatives are given: reference-based creation requires read_youtube_link first and its link as referenceUrl, autopilot must be enabled afterwards via set_autopilot "after the user agrees", and the new channel must have its own name and angle rather than copying. The "Free" note also tells the agent when cost is not a blocker, which no sibling tool states.

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

All ClipFlux tools Inspect

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

Need Help?