Skip to main content
Glama
ScientiaAI

@textile-designer-ai/mcp

by ScientiaAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Design Generation

td_design_generation

Generate new textile designs from a source image and a written prompt, re-imagine an image with textures or color palettes, or repaint masked areas; results are saved to disk.

Instructions

Design Generation: generate a new design from the source image plus a prompt (text_to_image, recommended), re-imagine it with a texture / colour palette (image_to_image), or repaint a masked area (inpaint). The website's Mood Board is not available here. Best for: creating a new design from your image plus a written prompt. Result files are saved to disk and their paths returned.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoMode: text_to_image (Image+Text to Image, Recommended): Generates a new design from the source image plus a prompt. prompt is required. image_to_image (Image to Image): Re-imagines the source image with a texture (fabric / surface treatment) and a colour palette; no prompt. inpaint (Inpaint): Repaints only the masked area of the source image from a prompt. Needs mask_image (same size as the image; white = area to change, black = keep) and prompt. Required: pass the mode the user named. If the user did not name one, omit it and the tool returns the modes to show them; never choose for the user.
waitNoWait for the job and save the outputs (default true). false returns the task_id right after submit.
imageYesSource image: a local file path or an http(s) URL. PNG, JPEG or WebP, up to 80 MB and 5000 px per side.
promptNoPrompt (text_to_image, inpaint): describe the design to generate, or what to paint in the masked area (required in those modes).
textureNoTexture Type: none (None, Recommended), smooth (Smooth), rough (Rough), linen (Linen), corduroy (Corduroy), silky (Silky), metallic (Metallic), matte (Matte), glossy (Glossy), woven (Woven), knitted (Knitted), leather (Leather), velvet (Velvet), denim (Denim), embroidery (Embroidery). Required: pass the mode the user named. If the user did not name one, omit it and the tool returns the modes to show them; never choose for the user. image_to_image only. Call describe_tool for what each option does.
mask_imageNoinpaint: the mask (path or URL), the same size as the image; white = area to change, black = keep.
output_dirNoFolder to save results in. Default: the folder of the input image (or the current directory for URL inputs). Files are never overwritten.
aspect_ratioNoAspect Ratio: same_as_input (Same as input image, Recommended): Matches the source image: square (1:1), landscape (4:3) or portrait (3:4). 1:1 (1:1): Square output. 4:3 (4:3): Landscape output. 3:4 (3:4): Portrait output. Required: pass the mode the user named. If the user did not name one, omit it and the tool returns the modes to show them; never choose for the user. text_to_image only.
color_paletteNoColor Palette: none (None, Recommended), Sunset Glow (Sunset Glow), Ocean Breeze (Ocean Breeze), Forest Mist (Forest Mist), Lavender Dreams (Lavender Dreams), Citrus Burst (Citrus Burst), Rainbow Splash (Rainbow Splash), Cotton Candy (Cotton Candy), Deep Ocean (Deep Ocean). Required: pass the mode the user named. If the user did not name one, omit it and the tool returns the modes to show them; never choose for the user. image_to_image only. Call describe_tool for what each option does.
estimate_onlyNoOnly return the credit estimate; nothing is uploaded or charged.
palette_colorsNoimage_to_image: up to 20 hex colours used as the palette instead of a named color_palette.
review_settingsNoOmit it and the tool first asks whether to use the recommended settings or adjust them (unless the call already sets some). true: ask each setting one by one. false: run with the given or recommended settings without asking; pass it only after the user chose that.
timeout_secondsNoHow long to wait for the job before returning its task_id (default 240).
unlimited_bundleNoRequest the Unlimited bundle for this run (only has effect on Unlimited plans; the server decides).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false), so the description's added job is behavioral context, and it delivers: results are written to disk with paths returned, and the Mood Board capability is absent. It stops short of stating that long jobs submit asynchronously and return a task_id (that detail lives only in the wait/timeout schema text), so it is not fully self-contained.

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?

Three front-loaded sentences: mode enumeration, scope exclusion, recommended use case, and output behavior. Efficient overall, though the 'Best for' sentence partially restates the text_to_image mode already described in the first sentence.

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, enum-heavy tool with 100% schema coverage and no output schema, the description covers the essentials an agent cannot get from structured fields: which mode corresponds to which intent, the recommended default, the Mood Board exclusion, and where results land. Nothing critical 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 already documents mode semantics, required fields, enums, file constraints, and the review/wait/estimate flow in detail. The description adds little parameter-level meaning beyond echoing the mode names, so the baseline 3 applies.

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 specific verbs and resources across all three operating modes (generate/re-imagine/repaint a design), naming the mode enum values inline so an agent can map user intent to mode without opening the schema. It also scopes the tool by noting the website's Mood Board is not available here, which prevents a plausible wrong selection.

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 per-mode when-to-use guidance and an explicit 'Best for' default (image plus written prompt), which is exactly the routing information an agent needs. What's missing is differentiation from close siblings such as td_design_creation, td_sketch_to_design, or td_design_extension, so the agent must still infer which of those to pick.

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