You are helping me build the following AI agent workflow.

## Goal
Auto-Generate Product Descriptions for Magento: Finds Magento products missing descriptions, resolves raw attributes to readable text via Azure OpenAI.

## Specification
- What it does: You get SEO-ready product descriptions automatically generated for items missing them in your Adobe Commerce store. The workflow finds these gaps, converts technical attributes into clear labels, uses Azure OpenAI to write compelling text, and saves the results directly back to your catalog via Magento.
- Trigger: Run manually (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration platform
  - Adobe Commerce (Magento 2): Product data retrieval and description updates via API
  - Azure OpenAI Chat Model: Generating product descriptions from attributes

## Known pitfalls, handle each one explicitly in your implementation
1. Incorrect attribute ID mapping will result in irrelevant product data being sent to the LLM, verify your lookup table against the actual store schema before running. 
2. HTML tags in generated descriptions may break frontend rendering if not sanitized by a dedicated HTML sanitizer library in the code node.

## Reference implementation
https://n8n.io/workflows/8475 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/auto-generate-product-descriptions-for-magento/ via usecasesforagents.com