Loading page
About this tool
Build a structured product listing prompt with attributes, benefits and keyword slots inside real field limits.
This builder assembles a single structured prompt for writing a product listing, made up of a role line, your verified attributes, the benefits to lead with, a keyword placement plan and hard output limits. Keywords are allocated across title, bullets and description so no phrase is repeated in every field, and the length rules follow the Google Merchant Center product data specification — 150 characters for a title, 5,000 for a description. It is aimed at sellers and marketers who want listing copy grounded in real product facts instead of invented specifications.
Open Ecommerce Listing Prompt Builder on AltFTool — it loads instantly in your browser.
Add your input to the workspace.
Adjust the options until the result looks right.
Copy or download the output and put it to work.
The primary phrase goes to the title and the rest are dealt one per bullet, with a two-mention cap.
The prompt instructs the model to write [CONFIRM] instead of guessing any missing specification.
Title, description and meta description lengths are stated in the prompt so the output arrives usable.
Aim for 60 characters or fewer, because that is roughly what Google shows before truncating a result. The technical ceiling is higher — the Google Merchant Center title attribute accepts 150 characters — but anything past the truncation point is invisible to most shoppers.
Two to six related phrases is usually enough for one listing. Beyond that the phrases start competing with each other and the copy reads as stuffed; this builder caps the plan at 20 and spreads them so no single phrase appears more than twice.
The Google Merchant Center description attribute accepts up to 5,000 characters. In practice 100-200 words of scannable copy converts better than a long block, so the builder asks for a word target and states the 5,000-character ceiling as a hard limit rather than a goal.
Search guidance judges content by usefulness and accuracy rather than by how it was produced, so the risk is not the tool but the output — invented specifications, duplicated boilerplate across variants and unsupported claims. Review every generated listing against the real product before publishing.