QR Branding

Generate a QR code from a prompt (AI)

qr_generate_ai

Generate branded QR codes from a natural-language design prompt, letting an LLM choose colors and shapes while encoding your text or URL.

Instructions

Generate a QR code where the QR Branding LLM picks colors and shapes from a natural-language prompt. Best for "make me a luxury gold dotted QR for a coffee brand" style requests.

Input Schema

Name	Required	Description
`prompt`	Yes	Natural-language design brief. The engine's LLM will pick colors, shapes, and style hints from this. Example: "luxury gold dots for a coffee brand".
`content`	Yes	The text or URL the QR will encode.
`logoUrl`	No	Optional logo URL to embed at the center.
`fileFormat`	No	Output format. Defaults to "png".
`outputWidth`	No
`stylePreset`	No	Optional style preset name (e.g. "minimal", "luxury", "playful"). Guides the LLM but does not override the design fully.
`outputHeight`	No

Output Schema

Name	Required	Description
`format`	Yes	File format the engine rendered: png, svg, jpg, webp or pdf.
`content`	Yes	The text or URL the QR encodes.
`filePath`	No	PDF in the stdio package only: local temp file the PDF was written to.
`mimeType`	No	MIME type of the rendered file (the engine's contentType).
`sizeBytes`	No	Size of the rendered file in bytes, as reported by the engine.
`resourceUri`	No	PDF on the remote server only: URI of the embedded resource block that carries the file.
`aiExplanation`	No	The design model's explanation of its choices, when the engine returns one.
`safeModeApplied`	No	True when the AI design did not scan and the engine re-rendered it in safe mode.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.4Oct 18, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent, and closed-world, so the safety profile is covered. The description usefully conveys that output is LLM-determined and thus variable, but says nothing about response shape, latency, or whether the result is returned inline or as a URL (though an output schema exists).

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 tight sentences: the mechanism and its distinguishing AI behavior come first, the use-case example second. Nothing is redundant or padded.

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 an output schema handling return values and annotations covering safety and determinism hints, the remaining need is when-to-use, which the example clause addresses. Only the absence of explicit sibling routing keeps it from full completeness.

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 coverage is 71% and the schema already documents prompt, content, logoUrl, fileFormat, and stylePreset. The description reinforces the prompt's purpose with a concrete example, but adds no syntax, format, or constraint detail beyond what the schema provides, so it sits at the baseline.

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 and resource ('Generate a QR code') and specifies the mechanism (a branding LLM picks colors/shapes from a prompt), which separates it from plain qr_generate and the template/builder siblings. It stops short of naming those siblings explicitly, so differentiation is implied rather than stated.

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?

The 'Best for "make me a luxury gold dotted QR for a coffee brand" style requests' clause gives a concrete use-case trigger that tells an agent when this tool is the right pick. It offers no explicit when-not or named-alternative routing (e.g., use qr_generate for exact control), leaving a small gap.

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

Deploy Server