HOW TO CALL THIS TOOL — read before every call: Decompose the user's request into filters first. Only what's left over goes in query. STEP 1: brand name → brand filter. STEP 2: product category → category filter. STEP 3: price → min_price/max_price. STEP 4: RAM, storage, screen size, resolution, refresh rate, wattage, Wi-Fi generation → constraints. STEP 5: what remains → query. BAD: query='Sony headphones under £200' | GOOD: brand='Sony', category='Headphones', max_price=200, no query. BAD: query='tablet' | GOOD: category='Tablets', no query. BAD: query='macbook neo' | GOOD: brand='Apple', category='Laptops', query='neo'. BAD: query='Samsung QLED TV' | GOOD: brand='Samsung', category='TVs', query='qled'. If brand+category alone cover what the user wants, omit query entirely. Only put differentiating terms in query: model lines (neo, ultra, oled), variants, model numbers (WH-1000XM5, s25 ultra). Query words must appear in the title, except words naming the category ('router' in Networking) and bare numbers or specs ('4070', '16GB'), which are ignored when finding products and only rank them. Put a model number with its prefix ('RTX 4070', not '4070') and check each title for it. Leave out use-case words like gaming, cheap or best. CROSS-CATEGORY NOTE: Gaming headsets → category='Headphones', query='gaming headset'. The Gaming category is consoles/controllers/accessories only. Always set lite=true (it still carries `attributes`). If 0 results, broaden the query or drop filters (but never present a near miss as meeting a requirement). Searches 26,000+ UK electronics products across 7 retailers with price comparison. Prices are in GBP. Every listing is new (refurbished and used are excluded). PRICE COMPARISON: for a final pick with offer_count > 1, get_product returns offers[] (sorted in-stock first, then cheapest): show the cheapest in-stock retailer, the other prices with the difference and the exact saving among in-stock offers. Before claiming a saving, read offers[].title (from get_product): they must name the same model; if they differ, don't claim one. Before recommending any pick, check its title is the product type asked for (not a cable, accessory or adapter). COMPARING SPECS: compare products from the `attributes` in the search results, not by calling get_product on each. Every spec known for a product is there as {status, value}, or {status, values} when conflicting, without sources; names and units are as in `constraints`. 'confirmed' (two or more retailers state the same value) and 'inferred' (one retailer's title states it) are both the product's spec: state the value. Only `conflicting` (retailers disagree: say so, don't pick one) or a missing name (unknown) needs a caveat. A product with no `attributes` has none of these seven specs known: say so only if the user asked about one. Call get_product only for your final 1-3 picks, and only when you need what search lacks: what only the retailer's description has (processor, GPU, ports, weight, battery), or every retailer's offer and buy link (search results carry only the best offer's purchase_url (cheapest in stock)). A pick with offer_count 1 needs no call unless the user asked for a description-only detail. Don't guess those details from titles. SPEC REQUIREMENTS: put exact requirements in `constraints`, not in query, and always set `category` (and brand if known) with `constraints`: a search of only specs is rejected. If a requirement is ambiguous (e.g. '16GB' could be RAM or storage), ask the user or search without that constraint. With constraints, every product has `constraint_status` per name: 'matched' = a retailer's title states a value that meets it. 'unverified' = not known to meet it: check `attributes[name]`, where `conflicting` means retailers disagree and missing means unknown. Never treat 'unverified' as a match or say a product meets a requirement because it was returned: tell the user it is unconfirmed. Products whose stated value fails are left out (`excluded_by_constraints`). Matched results come first, also with sort='price_asc'. With constraints, `total` counts the products that match every constraint and `unverified_total` the unverified products that passed the other filters (only some may be in `products`). If `total` is 0, say no product is known to meet every requirement and offer the unverified ones only as unconfirmed. If `candidates_truncated` is true, the first 2,000 candidates in the chosen sort order were checked and more exist: add a brand or category, or a narrower query, and search again before saying nothing matches. If the search was already narrowed, tell the user the results may be incomplete. STOCK: availability is in_stock, low_stock, out_of_stock or unknown (the retailer gave no stock signal: say so, don't assume). When availability is out_of_stock, mention it as an alternative and suggest checking back — do not silently omit it. purchase_url is a trustrails.app/go/ redirect through an affiliate link; TrustRails may earn a commission, and the price is the same. Colour variants have separate barcodes and are separate products: when price matters, search again without the colour or check other colours of the same model.