{
  "id": "E02",
  "url": "https://cartforagents.com/guides/humidifier-product-data",
  "title": "Humidifier product data: publish noise, room coverage and runtime",
  "description": "Map noise, area, output, tank and runtime claims to modes, conditions and sources, using a dated numeric-versus-vague Catalog example.",
  "answer": "Publish every humidifier fact as a number with its unit and the setting it applies to: noise in dB with the setting, distance and method; room coverage in ft² and m²; mist output in mL/h; tank size in litres; and runtime in hours on a named setting. Then check what Shopify's catalog actually carries, because its generated spec lists can add, drop or change values. In one catalog search, only 4 of 10 product descriptions printed a decibel figure, and none gave the conditions behind it.",
  "take": "For humidifiers, the decibel figure with its setting is the most valuable fact you can publish. Shoppers ask how quiet it is, and in our simulation, a plain \"quiet humidifier\" ask went to listings that answered with a number.",
  "summary": "A decibel figure only helps when its setting, distance and source travel with it. Here is the humidifier record to publish, checked against ten real catalog listings.",
  "claims": [
    {
      "text": "For the search \"humidifier for dry winter air large room quiet top fill\", a decibel figure appeared in the description of 4 of the 10 listings returned (positions 2, 3, 5 and 7: 21, 26, 28 and 26 dB), and none of those 4 descriptions named the setting, distance or test method. Counting Shopify-generated metadata as well, 6 of the 10 listings carried a decibel figure (adding positions 6 and 9). No title carried one.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "One search, one unpersonalized snapshot. The 4 counts the description field; the 6 adds Shopify-generated metadata. Counts listings, not market share, and measures what was written, not how loud any unit is."
    },
    {
      "text": "In the same result, the position 2 description read \"21dB Quiet\", while the position 4 description said the unit \"runs quietly enough to leave on overnight\", with no decibel figure. Position 4 carried no Shopify-generated metadata at all. Position 8 described itself as \"ultra-quiet\".",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "A difference in what was written, not in measured noise. The order of results does not show that a number helped or that words hurt."
    },
    {
      "text": "In the same result, a room area appeared in 4 of 10 descriptions, none with the conditions behind it; a runtime appeared in 8 of 10 descriptions, 2 of which named the setting; and \"top fill\" appeared in 7 descriptions plus 1 title.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "Description field only, unless a title is named. Measures disclosure, not product performance."
    },
    {
      "text": "In the same result, a tank size appeared in 8 of 10 descriptions, and a mist output in mL/h appeared in 2 of 10 (positions 3 and 7, both 320 ml/h).",
      "source_title": "Cart for Agents: How we checked (humidifier product data)",
      "source_url": "https://cartforagents.com/guides/humidifier-product-data#how-we-checked",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "Description field only, from the same single search. Shows what was published, not what the units do."
    },
    {
      "text": "Shopify's generated metadata carried noise claims that the merchant description we received did not make. Position 1's description said nothing about noise, while its generated feature list said \"Quiet operation ensures minimal disruption in any home environment\". Position 6's description said nothing about noise, while its generated spec list said \"Noise Level: As low as 26 dB\".",
      "source_title": "Cart for Agents: How we checked (humidifier product data)",
      "source_url": "https://cartforagents.com/guides/humidifier-product-data#how-we-checked",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "We cannot see what Shopify used to generate these fields; the values may come from merchant data we did not receive. Two records, not a rate."
    },
    {
      "text": "Position 5's description described a \"4-inch mist outlet\". Its generated spec list gave \"Mist Output: 4 inches (10.16 cm) with 30° tilting\", putting a nozzle size where an output rate would normally go. The same record's description said \"up to 32 hours\" while its generated spec list said \"Up to 36 hours\".",
      "source_title": "Cart for Agents: How we checked (humidifier product data)",
      "source_url": "https://cartforagents.com/guides/humidifier-product-data#how-we-checked",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "One record. We did not check the product or its manual, and we do not know which runtime is right."
    },
    {
      "text": "Position 10's generated spec list gave \"Maximum Room Area: 150 m²\", a value absent from its description; 150 also appears in the product's model name.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "We cannot confirm where Shopify's figure came from. It may come from data we did not receive."
    },
    {
      "text": "Position 3's description stated a 6.2 L tank, 320 ml/h output and up to 62 hours of runtime. At 320 mL/h the tank lasts about 19 hours, so the 62-hour figure implies an average near 100 mL/h, a lower setting the description did not name.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "inferred",
      "limitation": "Arithmetic on the stated figures only (6.2 L / 0.32 L/h). Real output varies with setting, humidity and water level; we did not test the unit."
    },
    {
      "text": "Position 4's description gave a 1.25-gallon tank and \"up to 36 hours on low\". 1.25 US gallons is about 4.7 L, so 36 hours implies an average output near 130 mL/h on low.",
      "source_title": "Cart for Agents: How we checked (humidifier product data)",
      "source_url": "https://cartforagents.com/guides/humidifier-product-data#how-we-checked",
      "source_date": "2026-10-26",
      "method": "inferred",
      "limitation": "Arithmetic on stated figures (4.73 L / 36 h). It is an implied average, not a published output rating; the merchant should take the real figure from the manual."
    },
    {
      "text": "Shopify says some Global Catalog response fields are generated or enriched by Shopify and marked Inferred, including the product description, technical specifications, top features and selling points. It says they may vary in accuracy and should be treated as discovery signals, not merchant-authored source text.",
      "source_title": "Shopify: Global Catalog MCP, Inferred response fields",
      "source_url": "https://shopify.dev/docs/agents/catalog/global-catalog",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Living developer documentation; the date is when we checked it, not a publication date. It does not say how the fields are generated or how any assistant uses them."
    },
    {
      "text": "Shopify says the Agentic section of the Shopify admin lets merchants review and change how product details are mapped to Shopify Catalog, and preview how products appear in Catalog search.",
      "source_title": "Shopify Help Center: Managing agentic storefronts",
      "source_url": "https://help.shopify.com/en/manual/online-sales-channels/agentic-storefronts/agentic-home",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Living help page checked on this date. It describes admin tools, not how any assistant ranks or displays a product."
    },
    {
      "text": "OpenAI says a product appears in ChatGPT's shopping carousel when ChatGPT perceives it to be relevant to the shopper's intent, considering the query and context such as Memory or Custom instructions.",
      "source_title": "OpenAI Help Center: Shopping with ChatGPT Search",
      "source_url": "https://help.openai.com/en/articles/11128490-shopping-with-chatgpt-search",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Living help article checked on this date. It lists inputs, not weights, and is not a causal ranking study."
    },
    {
      "text": "In a supplied-snippet simulation, an invented humidifier was placed among 7 real catalog listings and each model picked 2 of the 8, so chance is 25%. With vague copy it was picked in 3 of 180 sessions across three Claude models, 0 of 60 on GPT-6.1-Sol, 6 of 60 on Gemini 3.8 Flash and 3 of 54 on Gemini 3.1 Pro. With its facts as a spec line: 134 of 180, 20 of 60, 19 of 59 and 15 of 55. On GPT and Gemini it was picked in every session with a detailed shopper brief (20 of 20, 19 of 19, 15 of 15) and in 0 of 40 on each model with a one-line ask or no shopper. Claude picked it in 59 of 60, 32 of 60 and 43 of 60 for the same three briefs.",
      "source_title": "Cart for Agents: Vague vs specific product facts, simulated picks by Claude, GPT and Gemini models",
      "source_url": "https://cartforagents.com/research/vague-specific-product-facts-simulation",
      "source_date": "2026-10-27",
      "method": "controlled-simulation",
      "limitation": "Models chose from snippets we supplied, never opened pages and had no tools. The product and its facts were invented, every model had to pick two, and the detailed brief was written to fit the test product. API models, not the ChatGPT or Gemini shopping products. Not live visibility, rank or sales."
    }
  ],
  "sources": [
    {
      "title": "Cart for Agents: Receipts cited by our guides",
      "url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "accessed": "2026-10-27"
    },
    {
      "title": "Shopify: Global Catalog MCP",
      "url": "https://shopify.dev/docs/agents/catalog/global-catalog",
      "accessed": "2026-10-27"
    },
    {
      "title": "Shopify Help Center: Managing agentic storefronts",
      "url": "https://help.shopify.com/en/manual/online-sales-channels/agentic-storefronts/agentic-home",
      "accessed": "2026-10-27"
    },
    {
      "title": "OpenAI Help Center: Shopping with ChatGPT Search",
      "url": "https://help.openai.com/en/articles/11128490-shopping-with-chatgpt-search",
      "accessed": "2026-10-27"
    },
    {
      "title": "Cart for Agents: Vague vs specific product facts, simulated picks by Claude, GPT and Gemini models",
      "url": "https://cartforagents.com/research/vague-specific-product-facts-simulation",
      "accessed": "2026-10-27"
    }
  ],
  "limitations": [
    "The catalog examples come from one search in Shopify's agent catalog on October 26, 2026, with no shopper context. Ten listings, six of them from one seller, so the counts describe that result, not the humidifier category.",
    "We read what was written. We did not measure noise, coverage, output or runtime, and we did not check any listing against its manual.",
    "Where a value appears only in Shopify's generated lists, we cannot tell where it came from. It may come from merchant data we did not receive.",
    "The order of the ten results does not show why any listing ranked where it did. Nothing here shows that publishing a decibel figure raises a product in any assistant.",
    "The simulation used an invented product, supplied snippets and API models. It is not live ChatGPT, Gemini or Copilot behaviour, and it does not predict rank or sales.",
    "The record template and checklist are proposed. No platform requires this format, and we have not measured whether using it changes outcomes."
  ],
  "related": [
    "https://cartforagents.com/guides/humidifier-field-guide",
    "https://cartforagents.com/guides/spec-sold-product-guides",
    "https://cartforagents.com/guides/agent-ready-product-data",
    "https://cartforagents.com/research/quiet-humidifiers",
    "https://cartforagents.com/research/vague-specific-product-facts-simulation",
    "https://cartforagents.com/guides/product-specification-template"
  ],
  "published": "2026-10-27",
  "updated": "2026-10-27",
  "checked": "2026-10-27",
  "kind": "guide"
}