Skip to main content
Glama
industriesfatty-spec

Fattly

by industriesfatty-spec
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Generate an image

fattly_generate_image

Generate AI images from a text prompt or edit uploaded photos, then receive direct links to finished images. Spends credits only on successful generations, with automatic refunds if a generation fails.

Instructions

Generates an AI image from a prompt (or edits uploaded images). Returns links to the finished images. Spends credits: model price × numImages (see fattly_list_models); fails with an error if the balance is too low, and credits are refunded automatically when a generation fails. Prompts must be safe-for-work.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoModel id (default nano-banana-2). List: fattly_list_models.
promptYesDescription of the image to generate.
numImagesNoNumber of images 1–4 (default 1).
aspectRatioNoAspect ratio, e.g. 1:1, 16:9, 9:16 (default 1:1).
inputImageUrlNoOptional single input image for editing / face-swap models — must be a fal URL. Get one by uploading a local photo with fattly_upload_image.
inputImageUrlsNoOptional MULTIPLE input images (fal URLs) for multi-image edit models like nano-banana-2-edit / nano-banana-pro-edit. Typical swap use: image #1 = the scene/frame to keep (background, framing, lighting), image #2 = the subject/face to place into that scene. Get each URL from fattly_upload_image.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.2
    • changedInput schema / properties / inputImageUrls / description
      Previous value: -"Optional MULTIPLE input images (fal URLs) for multi-image edit models like nano-banana-edit / nano-banana-pro-edit / seedream-v4-edit. Typical swap use: image #1 = the scene/frame to keep (background, framing, lighting), image #2 = the subject/face to place into that scene. Get each URL from fattly_upload_image."New value: +"Optional MULTIPLE input images (fal URLs) for multi-image edit models like nano-banana-2-edit / nano-banana-pro-edit. Typical swap use: image #1 = the scene/frame to keep (background, framing, lighting), image #2 = the subject/face to place into that scene. Get each URL from fattly_upload_image."
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

The description discloses credit spending, cost calculation, failure behavior when balance is too low, automatic refunds, and the safe-for-work constraint. Since annotations are all false and do not describe side effects, the description itself carries the full burden and does so well.

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?

Three sentences with no filler: the main action is front-loaded, followed by output format, cost/error behavior, and a safety constraint. Every sentence carries essential information for correctly invoking the tool.

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?

The description covers purpose, output, cost, failure, refunds, safety, and edit workflows, and the schema fills in parameter details. With no output schema present, mentioning that links are returned is useful, though link format/details and whether generation is synchronous are not specified.

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?

The schema already documents all six parameters in detail, so the baseline is 3. The description adds value beyond the schema by explaining edit workflows, fal URL requirements, and the typical face-swap role of image #1 vs image #2, which the schema alone does not convey.

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 states a specific verb and resource ('Generates an AI image') and expands scope to edits of uploaded images, immediately distinguishing itself from the video/audio generation siblings. It also says it returns links, making the core function unambiguous.

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?

Clear context is provided: the tool is for image generation from prompts or edits, with references to fattly_list_models for model choice and fattly_upload_image for obtaining fal URLs. It does not explicitly name generate_video/generate_audio as alternatives, but the media-specific wording makes the choice obvious.

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

Deploy Server

Other Tools