Generate QR codes for URLs, vCards, WiFi, email, phone, SMS, calendar events, MeCards, X profiles, and plain text. No auth required.
Six tools with consistent, well-structured schemas and clear descriptions. All tools have verb-noun naming (generate_*), descriptions 50 - 150 chars (within baseline 34 - 392), and complete input schemas with type definitions and parameter descriptions. Tool annotations present (readOnlyHint, idempotentHint). Weaknesses: output schemas not documented (no structured response format specified); error handling guidance absent; no pagination or result limits documented despite base64 image returns; vCard tool has 20+ parameters creating cognitive load for LLM selection.
Generate a QR code that opens a pre-filled email. Scan to compose — recipient, subject, and body pre-set.
Generate a QR code containing plain text. Displays text when scanned — no internet needed.
Generate a QR code for a URL or website link. Scanned to open in browser.
Generate a QR code image from vCard contact data. Returns a base64-encoded PNG.
Generate raw vCard text (no QR code). Useful for .vcf file creation.
Generate a QR code for WiFi network credentials. Scan to connect — no password typing.
Output schemas not documented. Tools return base64-encoded PNG or vCard text, but response structure (field names, types, size limits) is not specified in tool definitions. LLMs cannot plan downstream operations or validate results.
No error handling guidance. Tools lack recovery hints for common failures (invalid email format, oversized vCard, unsupported characters). LLMs receive raw errors with no actionable next steps.
generate_vcard_qr parameter overload. 20+ parameters (firstName, lastName, prefix, suffix, org, title, phones array, emails array, addresses array, url, note, width, skin, darkColor, lightColor) create high cognitive load. LLM must reason about which fields to populate; consider splitting into simpler variants or accepting a single vCard object.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 64 | <=2025-11-25 | v2 |
No result limits or pagination documented. Base64-encoded PNG images can be large; no guidance on maximum width, file size, or whether results are streamed. Unbounded image generation could exhaust memory or context.
Parameter format constraints not explicit. 'darkColor' and 'lightColor' accept hex strings but no validation rule (e.g., '#RRGGBB' or 'RRGGBB') is documented. LLMs may pass invalid formats like 'red' or '0xFF0000'.