Skip to main content
Glama

Fattly

by io.github.industriesfatty-spec
OverviewDiscussionsAdmin

fattly_generate_ad_video

Ad Studio VIDEO ad (premium, ~150 credits): a real-looking creator presents your product on camera with a real voice — the full site flow. Takes a few minutes; the tool waits ~2 min and then returns an id to check with fattly_video_status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYesproduct = creator holds your product (needs productImageUrl). service = creator talks to camera, no product in frame. handsdemo = POV hands + product, NO face on screen, voice-over off camera (this is the site mode named: no avatar; needs productImageUrl). unboxing = silent ASMR unboxing, hands only, no speech — `script` is ignored, steer the shot with `prompt` instead.
voiceNoVoice name for non-EN locales.
localeNoSpoken language (default en). EN uses native Kling audio; others use Veo/TTS.
promptNoThe idea / how the shot should look (room, lighting, what the creator does). Not spoken — it directs the scene. Also the source we write the script from when `script` is empty.
scriptNoWhat the creator SAYS on camera, word for word. Keep it short — a few seconds of speech. Optional: with no script we write one from `prompt` for free. Ignored in unboxing mode (that ad has no speech).
actorIdNoAvatar you generated with fattly_create_avatar — the SAME creator presents the product.
consentNoREQUIRED (true) when you pass avatarUrl (your own creator photo). Must be true. By setting it you confirm that you have the rights to, and the consent of, every person who is visible or audible in the materials you provide.
settingNoScene id from fattly_list_ad_presets.
avatarIdNoCreator from the built-in roster (see fattly_list_ad_presets).
avatarUrlNoYour own creator photo as a fal URL. Using a photo of a real person requires consent: true.
unbrandedNoKeep the product free of invented branding.
templateIdNoAd preset id — must be a non-graphic preset (see fattly_list_ad_presets).
aspectRatioNoVideo shape: 9:16 vertical (default, TikTok/Reels) or 16:9 landscape.
productImageUrlNoProduct photo as a fal URL — REQUIRED for product mode. Use fattly_upload_image.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / avatarUrl / description
      Previous value: -"Your own creator photo as a fal URL."New value: +"Your own creator photo as a fal URL. Using a photo of a real person requires consent: true."
    • addedInput schema / properties / consent
      Added value: +{
+  "description": "REQUIRED (true) when you pass avatarUrl (your own creator photo). Must be true. By setting it you confirm that you have the rights to, and the consent of, every person who is visible or audible in the materials you provide.",
+  "type": "boolean"
+}
  2. Changed8 schema fields changed
    • addedInput schema / properties / aspectRatio
      Added value: +{
+  "description": "Video shape: 9:16 vertical (default, TikTok/Reels) or 16:9 landscape.",
+  "enum": [
+    "9:16",
+    "16:9"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / locale / description
      Previous value: -"Spoken language (default en). EN uses native Kling audio; others use TTS + avatar."New value: +"Spoken language (default en). EN uses native Kling audio; others use Veo/TTS."
    • changedInput schema / properties / locale / enum
      Previous value: -[
-  "en",
-  "pl",
-  "de",
-  "es"
-]New value: +[
+  "en",
+  "pl",
+  "de",
+  "es",
+  "fr"
+]
    • changedInput schema / properties / mode / description
      Previous value: -"product = creator holds your product (needs productImageUrl). service = creator talks to camera, no product in frame."New value: +"product = creator holds your product (needs productImageUrl). service = creator talks to camera, no product in frame. handsdemo = POV hands + product, NO face on screen, voice-over off camera (this is the site mode named: no avatar; needs productImageUrl). unboxing = silent ASMR unboxing, hands only, no speech — `script` is ignored, steer the shot with `prompt` instead."
    • changedInput schema / properties / mode / enum
      Previous value: -[
-  "product",
-  "service"
-]New value: +[
+  "product",
+  "service",
+  "handsdemo",
+  "unboxing"
+]
    • addedInput schema / properties / prompt
      Added value: +{
+  "description": "The idea / how the shot should look (room, lighting, what the creator does). Not spoken — it directs the scene. Also the source we write the script from when `script` is empty.",
+  "type": "string"
+}
    • changedInput schema / properties / script / description
      Previous value: -"What the creator SAYS on camera. Keep it short — a few seconds of speech."New value: +"What the creator SAYS on camera, word for word. Keep it short — a few seconds of speech. Optional: with no script we write one from `prompt` for free. Ignored in unboxing mode (that ad has no speech)."
    • changedInput schema / required
      Previous value: -[
-  "mode",
-  "script"
-]New value: +[
+  "mode"
+]
  3. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only cover the safety profile (non-read-only, non-idempotent, non-destructive, closed-world). The description adds genuinely non-obvious behavior: credit cost, multi-minute runtime, a hard ~2 minute wait ceiling, and the asynchronous id + fattly_video_status polling handoff. That is exactly the context an agent needs and cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences: the first front-loads what the tool produces and its cost, the second front-loads the latency and the follow-up call. Nothing is wasted and no parameter detail is redundantly restated.

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 14-parameter, no-output-schema generation tool, the description supplies the cost, the runtime, the wait/poll contract, and the next tool to call, while the fully-covered schema handles parameter semantics. Nothing an agent needs to invoke this correctly 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% and the schema itself carries rich per-parameter guidance (mode semantics, consent requirements, voice/locale behavior, cross-tool references). The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource (generate a VIDEO ad with a real-looking creator presenting the product on camera with a real voice) and pairs it with a price/latency signal. It implicitly separates this from the image-ad sibling fattly_generate_ad via 'VIDEO', but never names that sibling or fattly_generate_video explicitly, so the differentiation is left partly to inference.

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 gives clear operating context: a premium (~150 credits) tool that takes a few minutes, waits ~2 min, then returns an id to poll with fattly_video_status. That is real workflow guidance. However, it never states when to choose this over fattly_generate_ad, fattly_generate_video, or fattly_trend_video, and gives no exclusions.

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

All Fattly toolsInspect
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