Skip to main content
Glama

Make a fruit story

start_fruit_story
Destructive

Make an AI Fruit Story video (3D cartoon fruit people in a short soap opera). It spends credits from the user's MakeViral account (a scene that fails gives its credits back) and takes several minutes: this call returns at once, then call get_fruit_story with wait true. Send the cast (1-3 fruit people) and either your own story as draft (written with fruit_story_guide's prompts) or only an idea, and MakeViral writes it. Before calling, tell the user the price in credits (fruit_story_guide). Calling again with the same input within 10 minutes returns the first story.

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": {
      "cast": "<cast>"
    },
    "name": "start_fruit_story"
  }
}

Input Schema

NameRequiredDescriptionDefault
castYes1-3 fruit people
ideaNoOne line, or a few 'Name: line' lines the story must use
draftNoYour own story: the JSON the writer prompt of fruit_story_guide asks for (title, looks, numbers, scenes).
plotsNoUp to 2 plot ids (fruit_story_guide)
styleNo
captionsNo
languageNo
requestIdNoOptional id (8-64 letters, digits, - or _). The same id never charges twice.
sceneCountNoScenes of about 8 s each. Default 6.

Output Schema

NameRequiredDescriptionDefault
storyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations it discloses the traits that actually matter for a paid, async, open-world generation: it spends account credits, failed scenes refund their credits, the job takes several minutes but returns at once, and repeating the same input within 10 minutes returns the cached first story. The credit and refund semantics go well past destructiveHint=true, which only says 'this mutates something'.

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?

One dense paragraph where nearly every clause carries a distinct fact (cost, async handoff, input choice, price disclosure, dedupe window). It is a little crammed rather than strictly front-loaded by priority, but there is no filler.

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, nested-object, credit-spending generation tool, the description covers cost, timing, polling follow-up, input modes, and duplicate-call behavior. An output schema exists, so omitting return-shape detail is correct, and nothing essential to a successful invocation 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 67%, and the description closes the most important gap by explaining the draft/idea relationship — supply your own story JSON or just an idea and MakeViral writes it — plus the 1-3 cast size. It does not add detail for style, captions, language, plots, or sceneCount, which is acceptable given the schema covers those with enums and defaults.

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 first clause names a specific verb and artifact: 'Make an AI Fruit Story video (3D cartoon fruit people in a short soap opera).' That is concrete enough that an agent can separate it from start_legacy_story or start_story_video without opening any schema, and the parenthetical adds the content style that defines the resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the full call sequence explicitly: this call returns immediately, then use get_fruit_story with wait true; it also says to tell the user the price beforehand via fruit_story_guide and offers the draft-vs-idea choice. What is missing is any negative routing, e.g. when to prefer start_story_video over this tool, but the operational guidance for using this one is clear.

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