Skip to main content
Glama

Fattly

by io.github.industriesfatty-spec
OverviewDiscussionsAdmin

fattly_generate_video

Generates an AI video from a prompt (or from an image). Takes a few minutes — the tool waits up to ~2 minutes and returns a link to the mp4 file; if it is still rendering, it returns a generation id to check with fattly_video_status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNokling-3-standard | veo-3-1 | seedance-2-5 (default kling-3-standard).
promptYesDescription of the video scene.
consentNoREQUIRED (true) whenever you pass inputImageUrl or referenceImageUrls — animating a photo of a real person needs their consent. 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.
durationNoClip length in seconds (model dependent).
aspectRatioNoAspect ratio, e.g. 16:9, 9:16, 1:1 (default 16:9).
inputImageUrlNoOptional start image for image-to-video — must be a fal URL. Get one with fattly_upload_image.
referenceImageUrlsNoOptional MULTIPLE reference images (fal URLs, 2-50) for reference-to-video models like seedance-2-5 — the model blends them into one video. With a single URL the video starts from that image (image-to-video). Get each URL with fattly_upload_image.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / consent
      Added value: +{
+  "description": "REQUIRED (true) whenever you pass inputImageUrl or referenceImageUrls — animating a photo of a real person needs their consent. 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. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations confirm it is a non-readonly, non-idempotent, closed-world generator, and the description adds concrete behavior annotations don't carry: multi-minute latency, a ~2-minute wait window, and the two possible return shapes (mp4 link vs generation id). Consent and rights obligations are covered in the schema rather than the description, so this is good but not exhaustive.

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 tightly packed sentences with no filler. The async/timeout behavior and the fallback status tool are front-loaded so the agent learns the critical invocation consequence immediately.

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

Completeness4/5

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

With no output schema, the description correctly explains both return paths (mp4 link or generation id) and the polling follow-up, which is what an agent needs to handle the response. Only minor gaps remain, such as credit cost and where model names come from (fattly_list_models).

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%, so parameters like model, aspectRatio, consent, and the image URL fields are already well documented in the schema. The description only restates the prompt-or-image duality, adding little beyond what the schema already conveys, which fits the baseline 3.

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?

States a specific verb+resource ('Generates an AI video') and clarifies the two input modes (prompt or image), which is meaningful against siblings like fattly_generate_ad_video and fattly_trend_video. It does not explicitly differentiate itself from fattly_animate_photo, the closest neighbor for image-to-video, so it stops short of full sibling routing.

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

Usage Guidelines3/5

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

It gives clear follow-up guidance — poll with fattly_video_status if a generation id is returned — which is useful operational routing. However, it never states when to pick this tool over alternatives such as fattly_animate_photo or the ad-video generators, leaving the primary selection decision implied.

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