ClipFlux

Switch Autopilot on or off

set_autopilot

Switches a channel's Autopilot on or off and sets its schedule: the weekdays, the hour and time zone it makes a video, and the credit floor below which it pauses itself. With Autopilot on, ClipFlux makes a video on each scheduled day and spends that video's credits (and posts it, if the channel posts somewhere). Before switching it ON, tell the user the channel, the days and time, what one video usually costs (quote_video) and that it runs until they switch it off, and switch it on only after their yes in their own message. Switching off or changing the schedule needs no extra yes.

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": {
      "channelId": "<channelId>"
    },
    "name": "set_autopilot"
  }
}

Input Schema

Name	Required	Description
`on`	No	true switches it on (only after the user's yes), false switches it off. Leave out to change only the schedule.
`days`	No	Weekdays it makes a video, for example ["Monday", "Thursday"].
`hour`	No	Hour of the day, 0 to 23, in the time zone.
`timezone`	No	An IANA time zone, for example "Europe/Stockholm".
`channelId`	Yes	From list_channels or create_channel.
`pauseBelowCredits`	No	Pause before a run would leave fewer credits than this; null for no floor.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations (which only say it is a non-read-only, non-destructive, open-world write). It discloses the recurring side effects: a video is made on each scheduled day, credits are spent, and the result is posted if the channel posts somewhere, plus the pause floor that halts runs. The 'runs until they switch it off' framing makes the persistent, ongoing-spend nature clear, which is the key risk an agent must communicate.

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 with the core action, then the consequences, then the confirmation rules — a sensible order with no filler. The confirmation sentence is long and packs several instructions together, which is the only thing keeping it short of a 5.

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 six-parameter mutating tool with no output schema, the description covers what the agent needs to act safely: what gets scheduled, what gets spent, what gets posted, how long it runs, and the exact consent flow. Nothing material is missing.

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%, so the field meanings (on, days, hour, timezone, channelId, pauseBelowCredits) are already documented in the schema itself. The description restates the schedule components at a high level but adds no format or unit detail beyond what the schema provides, so this sits at the baseline.

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 ('Switches a channel's Autopilot on or off') and immediately enumerates what the call also governs: weekdays, hour, time zone and credit floor. No sibling tool in the list handles autopilot scheduling, and the description makes that scope unambiguous.

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 when-to-use rules with a required confirmation protocol: before turning it ON, tell the user the channel, days and time, cost via quote_video, and that it runs until switched off, and only act after a yes in their own message. It also carves out the inverse case — switching off or changing the schedule needs no extra yes — so the agent knows both branches.

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?