Skip to main content
Glama
Hermoso

Hermoso

Official

Make a series of faceless short videos (Content Factory)

make_series

Turn one topic into a series of faceless short videos, optionally matching a reference video's style, then quote, plan, render, and schedule episodes.

Instructions

CONTENT FACTORY: turn ONE topic into a SERIES of faceless short videos (narration over pictures, no presenter), optionally in the STYLE of a trending reference video. Give topic ("make a video about…"), episodes (1-10, default 1) or your own episodeTitles, durationSeconds (20-120 per episode, default 30) and optionally reference (a TikTok / Reel / Facebook / X link or a video file URL whose look, pacing and opening hook every episode copies, with plain subtitles only if the reference burns its own; never its words or characters). Find a trending reference with search_tiktok / search_instagram / search_youtube when the user wants one. THREE STEPS, ALWAYS IN THIS ORDER: (1) call with no confirm for a FREE quote of the whole series (per episode and total); (2) optionally planOnly:true to see the episode titles and the style card first (a small planning charge); (3) confirm:true (pass the plan from step 2 to reuse it) queues every episode and returns their job ids; poll get_job. To make MORE of a series later, pass its returned plan as moreOf: same style, no episode repeated, the reference not watched again. Each finished episode can be scheduled with this tool again: pass jobIds plus schedule {channels, at, everyHours, timezone} and it books one post per finished episode, spaced everyHours apart (default 24). Captions follow the reference (on if it burns words on screen) unless captions says otherwise.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "make_series"
  }
}

Input Schema

NameRequiredDescriptionDefault
planNothe `plan` a planOnly call returned, to run it without planning again
styleNooverride the look in words (e.g. "flat 2D cartoon") instead of the reference's
topicNowhat the series is about, in the user's words
voiceNonarrator: 'female' or 'male' (default follows the reference), or any narration voice name make_explainer takes
formatNorenderer lane: 'explainer' (default; exact length) or 'faceless_channel' (2K, whole 10s blocks)
jobIdsNoSCHEDULE MODE: the episode job ids to schedule (finished ones are booked)
moreOfNoMORE EPISODES: the `plan` an earlier call returned. Keeps its style and length, writes new episodes only
confirmNoREQUIRED true to start rendering (real spend). Without it you get a free quote
captionsNoburn subtitles of every spoken word. Default: on only when the reference itself burns its spoken words as subtitles, otherwise off; nothing else is ever put on screen (no app screens, URLs, cards or stickers) unless the user asks
episodesNohow many episodes, 1-10 (default 1)
get_costNotrue: return the price only; nothing runs or bills
planOnlyNowrite the episode plan and style card, render nothing (a small planning charge)
scheduleNoSCHEDULE MODE: where and when the first episode posts; the rest follow every `everyHours` (default 24)
referenceNoa video link whose style every episode copies
aspectRatioNodefault: the reference's shape, else 9:16
postCaptionsNoSCHEDULE MODE: one post caption per episode, in order (default: the episode title)
episodeTitlesNoyour own episode titles, in order (sets the episode count)
durationSecondsNolength of EACH episode, 20-120 seconds (default 30)
idempotency_keyNochosen once, resent unchanged on retries: the same key never buys twice
expected_creditsNothe get_cost price; refused unbilled if the live price differs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.532
    • addedInput schema / properties / expected_credits
      Added value: +{
      +  "description": "the get_cost price; refused unbilled if the live price differs",
      +  "type": "number"
      +}
    • addedInput schema / properties / get_cost
      Added value: +{
      +  "description": "true: return the price only; nothing runs or bills",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "chosen once, resent unchanged on retries: the same key never buys twice",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv0.1.519
    • addedInput schema / properties / moreOf
      Added value: +{
      +  "description": "MORE EPISODES: the `plan` an earlier call returned. Keeps its style and length, writes new episodes only"
      +}
  3. Changed2 schema fields changedv0.1.484
    • changedInput schema / properties / voice / description
      Previous value: -"narrator; default follows the reference"New value: +"narrator: 'female' or 'male' (default follows the reference), or any narration voice name make_explainer takes"
    • removedInput schema / properties / voice / enum
      Removed value: -[
      -  "female",
      -  "male"
      -]
  4. Changed4 schema fields changedv0.1.465
    • addedInput schema / properties / schedule / properties / at / description
      Added value: +"time of the first post: YYYY-MM-DDTHH:MM wall-clock, or an ISO date-time"
    • addedInput schema / properties / schedule / properties / channels / description
      Added value: +"channels to post each episode to, e.g. tiktok, instagram, youtube (as schedule_post takes them)"
    • addedInput schema / properties / schedule / properties / everyHours / description
      Added value: +"hours between episodes; default 24"
    • addedInput schema / properties / schedule / properties / timezone / description
      Added value: +"timezone name for at, as schedule_post takes it"
  5. Addedv0.1.454

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say non-readonly, open-world, non-idempotent; the description adds what genuinely matters: a free quote before any charge, 'a small planning charge' for planOnly, `confirm:true` meaning real spend, `idempotency_key` protecting against double-buying, and `expected_credits` being refused unbilled on price drift. It also discloses what the reference copies and what it must not (style/pacing/hook, never words or characters) and what is ever put on screen, which the annotations cannot express.

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?

It is front-loaded with purpose, then the mandated step order, then extension and scheduling modes — a sensible sequence with no filler sentences. It is dense, however: several sentences chain three or four clauses (the `reference` and captions sentences in particular) and pack many params into one paragraph, which costs some scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 20-parameter, multi-mode tool (quote / plan / confirm / moreOf / schedule) with a nested `schedule` object and no output schema, the description does cover each mode and says what step 3 returns ('their job ids; poll get_job'). Gaps remain around the quote's contents, what `moreOf` returns, and failure/refund behavior — the agent must infer the rest.

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?

With 100% schema coverage the schema already documents all 20 parameters, so the description needn't restate them — and it correctly focuses on relationships instead: `topic` vs `episodeTitles` setting the count, `plan` reuse across planOnly and `moreOf`, and `jobIds`+`schedule` forming a distinct scheduling mode. A few params (format, aspectRatio, voice, expected_credits) get no narrative treatment, leaving this just above baseline rather than at it.

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 opening states a specific verb+resource: 'turn ONE topic into a SERIES of faceless short videos (narration over pictures, no presenter)', and the 'series' framing plus 'optionally in the STYLE of a trending reference video' distinguishes it from the single-video siblings (make_explainer, make_motion_film). The later SCHEDULE MODE clause is also named explicitly, so an agent knows the tool has a second function 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?

It prescribes an explicit, ordered workflow ('THREE STEPS, ALWAYS IN THIS ORDER') and routes to alternatives by name: search_tiktok/search_instagram/search_youtube for finding a reference, get_job for polling, and `moreOf` for extending a series. It also states the exclusion condition implicitly by framing step 1 as free and step 3 as 'real spend', so an agent knows when not to pass `confirm`.

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

Deploy Server

Other Tools