Find Shopify stores with rising estimated traffic and active Meta ads.

Cost guard: before each paid Spytrend call, run the free `estimate_cost` with the same tool and arguments, estimate the cost and stay within the user's stated budget; if the user has not stated a budget, tell them the estimate before the first paid call. If pricing consent is required, show the returned terms and stop until the customer explicitly agrees; never accept on the customer's behalf. If a required call does not fit the stated budget, make no paid call and return `Budget limit prevents required research`; omit an optional call that does not fit and disclose reduced coverage. When opening ads with `get_ad`, skip multilang ads (`is_multilang`) and never call `get_media` after `get_ad`. Retry once only when `retryable=true`, after `retry_after_seconds`. Read `params.ignored` after every search; an ignored required filter never counts as applied. Cost notices are not part of the final customer report.
Use the connected Spytrend MCP to find Shopify stores in **ecommerce_and_retail** with returned country context **US**, a qualified increase in estimated traffic and independently verified active Meta advertising.

Execute every research stage in this prompt in one turn. Apart from mandatory pre-call cost notices, do not emit intermediate responses and do not stop after scope validation. Stop early only for invalid input or unavailable required evidence. Return only the final customer report.

1. Validate the supported Shopify category and country. Country is returned store-country or main-visitor-country context only; it is not country-specific traffic, headquarters, shipping or customers. Traffic must use the latest qualified complete monthly window.
2. Run the `correlated_growth` and `ad_growth_ahead` store-discovery routes sequentially with exact category, country, platform Shopify, `exclude_infrastructure=true` and `limit=5` each. Preserve the distinct signal meanings. Normalize domains, deduplicate by registrable domain and preserve returned route order.
3. Use the returned discovery rows directly as compact evidence. Normalize and deduplicate exact registrable domains. Never call `get_shop` or repeat `search_shops(q=domain)` for a returned discovery domain. Confirm Shopify identity, direct category fit, returned country context, latest complete-month global traffic estimate, traffic quality and returned growth signal.
4. Verify up to five compact-qualified candidates in retained order. For each, run one exact-domain Meta search sequentially for the selected country with active status and `limit=1`, then open at most one representative ad. Require detailed active status, country delivery, matching offer and exact first-party destination. A store qualifies only when both the traffic signal and active-ad gate pass. Aim for 3–5 qualified stores; end verification after five candidates or when the next search plus detail does not fit the stated budget, and disclose reduced coverage.
5. Traffic estimates and ad counts alone do not qualify a store. Do not infer country-specific traffic or causation. Required discovery/verification failure makes the run Partial; completed zero is Complete. Retry only on explicit `retry_after_seconds` guidance.

Write a table-free report of no more than 300 words. Show 3–5 qualified stores (fewer only when fewer qualify). Include offer, latest complete-month global estimated visits and period, qualified percentage change, returned signal group, verified active Meta evidence and one reason to inspect. Add `What stands out`, `Inspect first`, `Evidence & limits`, and useful unresolved relationships only when material.

Label merchant destinations `Website` or `Landing page`. Use `Evidence` only when MCP explicitly identifies a stable first-party research resource link. A merchant destination, image CDN, preview or media URL is never `Evidence`. Name the category and country in plain words, never as slugs or codes. Hide service name, internal labels, routes, tools, calls, raw IDs, UTC timing, elapsed time, tokens, retries, pagination and run summaries.

End exactly:

`Traffic figures are third-party estimates and Meta activity is observable evidence. Their relationship is correlational and does not prove conversions, revenue, ROAS or profitability.`

Only after `Show supporting record`, use retained responses for non-sensitive route and verification details without rerunning research.