Skip to main content
Glama

Make a faceless story video

start_story_video
Destructive

Make an AI Story Video (a faceless narrated short in the chosen format: what if, scary story, history, body facts, choose your path, cartoon story...). It spends credits from the user's MakeViral account (a part that fails gives its credits back) and takes several minutes: this call returns at once, then call get_story_video with wait true. Two ways: 1) your own script as draft (written with story_video_guide's prompts; MakeViral then only makes the video and charges no writer), or 2) only the idea (and the user's own story, if any), and MakeViral writes the script. Before calling: check it with check_story_video and tell the user the price in credits. Calling again with the same input within 10 minutes returns the first story.

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": "start_story_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
ideaNoOne line, e.g. 'What if the moon disappeared?'
paceNo
draftNoYour own script: the JSON the writer prompt of story_video_guide asks for (title, characters, places, scenes, choices, stats...).
musicNo
storyNoThe user's own full story, when there is one: the script keeps its events, names and facts
styleNoArt style. Default: the format's.
aspectNoDefault 9:16 (TikTok, Reels, Shorts).
formatNoThe video format. Default what-if. story_video_guide lists them with examples.
qualityNoHow many scenes move (AI clips) instead of stills. Default: the format's.
secondsNoLength in seconds. Default: the format's.
voiceIdNoNarrator voice id (story_video_guide). Default: the format's.
captionsNoCaption style. Default: the format's.
languageNoNarration language. Default en.
requestIdNoOptional id (8-64 letters, digits, - or _). The same id never charges twice.
continueFromNoPart 2 of a finished choose-your-path (or 'Part 2?') story of this user

Output Schema

NameRequiredDescriptionDefault
storyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=false but say nothing about cost. The description adds the economically critical behavior: it spends credits, failed parts are refunded, it runs for several minutes asynchronously while returning immediately, and repeat identical calls within 10 minutes return the original story rather than charging again. That is exactly the context an agent needs before triggering a paid mutation.

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 purpose, then cost/timing, then the two input modes, then the pre-call check - a deliberate ordering that matches how an agent decides and executes. Slightly dense in the opening parenthetical format list, which partly duplicates the `format` enum, but no sentence is wasteful.

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 15-parameter, nested-object, paid, asynchronous tool with an output schema, the description covers the missing pieces: cost and refunds, latency and the polling handoff, deduplication window, and the choice between pre-written and generated scripts. Return-value detail is correctly left to the output schema.

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 87%, so the enum and field docs already carry most weight and the baseline is 3. The description goes beyond it by explaining the semantic role of `draft` (must be the JSON the story_video_guide writer prompt asks for; suppresses the writer charge) versus `idea`/`story` (user's facts and names are preserved), which the schema alone does not make clear.

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 ('Make an AI Story Video' - a faceless narrated short) and immediately scopes it with the format family list. It names the siblings it hands off to (get_story_video, story_video_guide, check_story_video), so an agent can distinguish it from the other start_*_story tools without opening a 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?

Gives an explicit pre-call sequence ('check it with check_story_video and tell the user the price in credits'), an explicit post-call sequence ('this call returns at once, then call get_story_video with wait true'), and a decision rule between two input modes: supply `draft` to skip the writer, or supply only `idea`/`story` to have MakeViral write it.

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