How to Write Google Merchant Center Title and Description
Merchant Center copy mints 4.8 stars and a GTIN. Attributes had a two-pack strainer and no price. Print counts vs 150 and 5000.
The matching generator is the Google Merchant Center Title and Description from Attributes (No Invented Ratings) (Google Merchant Center Title Description From Attributes No Invented Ratings) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Title from brand plus pasted nouns
Write Google Merchant Center title and description from product attributes. Honor character caps. No invented ratings, GTIN, or reviews. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Attributes (id, title parts, brand, color, size, material, count): [Attrs]
Title cap I lock: [TitleCap or 150]
Description cap I lock: [DescCap or 5000]
Brand I may use (or UNKNOWN): [Brand]
GTIN as pasted (or UNKNOWN): [GTIN]
Words I must not use: [Banned]
What I must never invent (ratings, GTIN, price): [Never]
Output format: [Format]
Language: [Lang]
Channel I lock: [Channel or Google Merchant Center]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Honor the 150-character title cap
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Attrs nouns, Brand, GTIN, TitleCap, DescCap, Channel, Lang. Forbidden: star ratings, review counts, invented GTIN, invented price.
- Title: Brand + product nouns from Attrs. Print character count vs TitleCap. No ALL CAPS spam. No promotional extras not in Attrs.
- Description: facts from Attrs only. Print count vs DescCap. No 'top rated'.
- Attribute echo: brand, color, size, material, count as pasted or NOT IN INPUTS.
- GTIN: quote GTIN or UNKNOWN. Do not mint EAN/UPC.
- Refuse: Google Ads RSA headlines, GBP weekly posts, fake 4.8 stars.
- Never: do not invent a sale price or 'free shipping' if not in Attrs.
- Compliance pass: quote Banned and Never hits. Print counts. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Leave GTIN UNKNOWN if it was blank
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Merchant Center title and description from Attrs. Not Google Ads RSA and not GBP posts.
- Never invent ratings, GTIN, or prices.
- Honor TitleCap and DescCap.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Refuse RSA headlines and fake ratings
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (google merchant center title, merchant center description from attributes, no invented merchant ratings) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.