Skip to main content
Glama

Make a legacy story

start_legacy_story
Destructive

Make an AI Legacy Story: a 3D animated film of the user's life, business or family story, told in on-screen dialogue, with the user's real photos at the end. It spends credits from the user's MakeViral account (a scene that fails gives its credits back) and takes about 10-15 minutes: this call returns at once, then call get_legacy_story with wait true. Two ways: 1) your own script as draft (write it with legacy_story_guide's rules; MakeViral then only makes the film and charges no writer), or 2) only the story text, and MakeViral writes the script. Before calling: check it with check_legacy_story, tell the user the price in credits, and with photos ask the user to confirm the people in them are them or agreed, and that no one is a child. Photos: references are the photos the characters and places are drawn from (a person, a logo, a screenshot), each with the id the script uses, and its photo as photoUrl or as the next chat file in referencePhotos. proofPhotos / proofPhotoUrls are the real photos the film ends on. 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": {
      "story": "<story>"
    },
    "name": "start_legacy_story"
  }
}

Input Schema

NameRequiredDescriptionDefault
draftNoYour own script, in the shape legacy_story_guide shows: title, characters, places, blocks (scenes of shots), proofLines.
modelNoVideo model. Default minimax-h3 (sharpest, keeps each voice).
musicNoMusic bed. Default legacy (dark trap beat, big lift at the end).
storyYesThe story in the user's own words: who, where, the turning points, the real names, numbers and years
styleNoLook. Default pixar-3d (3D animated film).
qualityNoSize; must be one the model offers (legacy_story_guide). Default: the model's default (H3: 768p).
secondsNoTarget length of the animated part. Default 60. With your own script, its scenes set the length.
captionsNoBig burned-in captions of the lines. Default big.
languageNoLanguage of the spoken lines. Default en.
requestIdNoOptional id (8-64 letters, digits, - or _). The same id never charges twice.
referencesNo
proofPhotosNoReal photos the film ends on, attached in the chat
photosConsentNoNeeded with photos: true only after the user confirmed everyone in them is the user or agreed, and no one is a child
proofPhotoUrlsNoReal photos the film ends on, as public https links
referencePhotosNoThe reference photos attached in the chat, in the order of the references without a photoUrl

Output Schema

NameRequiredDescriptionDefault
storyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the annotations it discloses credit consumption, credit refund on a failed scene, the 10-15 minute runtime, and the asynchronous return-immediately contract. It also describes a 10-minute dedupe window ('calling again with the same input within 10 minutes returns the first story'), which is a nuance the idempotentHint=false annotation alone does not convey and does not directly contradict it. The main omission is that destructiveHint=true is never spelled out in terms of what is irreversible beyond credit spend.

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 the outcome and the cost/async contract before branching into the two modes and photo rules, and nearly every sentence carries operational information. It is a single dense paragraph, though; splitting the preconditions and the photo rules into separate sentences or bullets would make the scan faster for a 15-parameter tool.

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 destructive, open-world, asynchronous generation tool with 15 parameters and a nested draft schema, the description covers cost, timing, failure refunds, idempotency window, consent gating, photo plumbing, and the follow-up polling call. With an output schema present, it is not obligated to describe return values, and nothing an agent needs to call it correctly appears 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 93%, so the baseline is 3; the description earns an extra point by explaining cross-parameter relationships the schema cannot: `draft` versus `story` as alternative paths, that `references` ids are what the script's refId/refIds point at, and that referencePhotos are consumed in order for references lacking a photoUrl. It also ties `photosConsent` to the consent check the agent must perform first.

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 description opens with a specific verb and artifact: 'Make an AI Legacy Story: a 3D animated film of the user's life, business or family story, told in on-screen dialogue, with the user's real photos at the end.' It distinguishes this from siblings by naming the follow-up reader (get_legacy_story), the validator (check_legacy_story), and the authoring rules source (legacy_story_guide).

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 gives explicit preconditions (run check_legacy_story first, tell the user the credit price, obtain consent that photo subjects are the user or agreed and none is a child) and an explicit postcondition (call get_legacy_story with wait true). It also states the two mutually exclusive invocation modes: supply `draft` for your own script, or supply only `story` to let 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