Skip to main content
Glama

Fattly

by io.github.industriesfatty-spec
OverviewDiscussionsAdmin

fattly_edit_video

Draw-to-Edit: edits a REGION of a video using a mask + a text instruction (e.g. "make the car burn", "remove the person", "replace with a red car"). The masked area (WHITE on the mask, BLACK elsewhere) is regenerated across the whole clip, the rest is kept. Source video AND mask image must both be fal URLs (get them with fattly_upload_image). Takes a few minutes; returns the mp4 link, or a generation id to check with fattly_video_status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesWhat should happen to the masked area.
consentYesMust 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.
maskUrlYesMask image, fal URL. WHITE = area to edit, BLACK = keep unchanged.
videoUrlYesSource video, fal URL (from fattly_upload_image).
resolutionNoOutput resolution (default 720p).
durationSecondsNoClip length in seconds, 2-12 (default 5).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / consent
      Added value: +{
+  "description": "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"
+}
    • changedInput schema / required
      Previous value: -[
-  "videoUrl",
-  "maskUrl",
-  "prompt"
-]New value: +[
+  "videoUrl",
+  "maskUrl",
+  "prompt",
+  "consent"
+]
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare non-read-only/non-idempotent/non-destructive, and the description adds real behavioral value on top: the operation takes a few minutes, returns an mp4 link or an async generation id, and the unmasked area is preserved. It omits failure modes and any credit/cost implications.

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?

Short and front-loaded: it identifies the tool, then the mask semantics, then prerequisites, then runtime/return behavior. Every sentence carries information an agent needs.

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?

With no output schema present, the description compensates by describing the return value (mp4 link or generation id) and the polling path. Combined with a fully documented 6-parameter schema, an agent has everything needed to call and follow up on this tool.

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 100%, so the baseline is 3. The description still adds meaning by restating the WHITE-edits/BLACK-keeps mask convention in operational terms and giving example prompts that show what a usable 'prompt' value looks like.

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?

Names the tool's distinctive mechanism (mask + text instruction regeneration of a REGION) with three concrete prompt examples, so an agent can tell it apart from sibling image-editing tools like fattly_inpaint and from whole-video generators.

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?

Gives clear operating context: inputs must be fal URLs obtainable via fattly_upload_image, and results come back directly or as a generation id checked with fattly_video_status. It does not explicitly contrast when to pick this over region-adjacent siblings such as fattly_inpaint, so it stops short of a 5.

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