analyze_product
Deeply validate ONE TikTok Shop product before committing money or content to it. Give it a product_id from product_scout (or any TikTok Shop product URL) and it reads the listing, samples reviews across the full depth rather than only the most recent page, pulls comparable competitors, and returns what buyers actually say. You get: provider-reported sold / review / rating / price evidence; buyer voice split into what buyers praise and what they complain about; unmet needs and purchase objections in buyers' own words; return and fulfilment signal; a Why Now read; competitor intelligence and where rivals are weak; risks separated into product risks, market risks and data-confidence risks; and a 'how to beat this' synthesis of concrete differentiation angles traced back to specific review evidence. Every section states whether it resolved - provider facts, HookLayer analysis and genuinely unavailable evidence are distinguishable, and thin evidence is reported as thin rather than filled in. There is no revenue or GMV output and sold counts are never multiplied by price. Use product_scout first to find candidates, then this to decide between them. Cost: 10 credits. Requires the shop_intelligence entitlement.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "analyze_product"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| market | No | 2-letter ISO region code or 'GLOBAL'. Defaults to US. Should match the market the product was found in. | |
| product_id | No | TikTok Shop numeric product id, as returned by product_scout in opportunities[].product_id. Supply this or product_url. | |
| product_url | No | Any TikTok Shop product URL (tiktok.com/shop/pdp/..., shop.tiktok.com/.../pdp/..., /view/product/...). Used when the user pastes a link instead of an id. | |
| include_competitors | No | Default true. Competitor discovery and the cross-product buyer-pain map are the differentiated part of this report; set false only when the caller explicitly wants the single-product read and fewer provider calls. The credit cost is the same either way. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| region | No | ||
| success | Yes | ||
| economics | No | Price and margin context. Contains no revenue or GMV figure. | |
| fetched_at | No | ||
| product_id | No | ||
| provenance | No | Endpoints called, provider call count, staleness, and which fields the model wrote. | |
| buyer_voice | No | Review sample summary including rating histogram and sampled count. | |
| competition | No | Percentile placement against the peer set, when one was resolvable. | |
| analyst_read | No | Model-written operator summary grounded in the sections above. Falls back to a deterministic version if the model call fails. | |
| market_proof | No | Demand evidence section. Carries available / headline / data / evidence / risks / unknowns / confidence. | |
| buyer_pain_map | No | Themes shared across this product and its competitors, with differentiation candidates. Rates are per-product, so a deeply sampled product does not outweigh a shallowly sampled rival. | |
| analyst_verdict | No | Deterministic verdict and confidence. | |
| creator_content | No | ||
| source_coverage | No | Which sections resolved and which did not. | |
| validation_read | No | Extended validation narrative. Null when include_competitors was false. | |
| content_patterns | No | ||
| current_evidence | No | Composite score from currently observable evidence, with what was unavailable. | |
| evidence_classes | No | Explicit map so the host never has to guess provenance: fact[] came from the provider, analysis[] was derived by HookLayer, unavailable[] had insufficient evidence. | |
| product_identity | No | title, shopName, category, productUrl, imageUrl. | |
| credits_remaining | No | ||
| recommended_chain | No | Suggested next calls, chosen from the evidence this analysis actually found. SUGGESTIONS ONLY - present them and let the user pick. Do not call them automatically; each one costs the user credits. | |
| competitor_landscape | No | Comparable products and where they are weak. available:false when competitor discovery did not resolve. | |
| evidence_interpretation | No | Why Now plus risks split into product / market / data_confidence, each citing the observation that triggered it. Only claims what is observable now; never asserts a trend it has no history for. | |
| buyer_voice_intelligence | No | Opportunity-grade review read: sampleComposition, love, painPoints, unmetNeeds, purchaseObjections, returnSignal, fulfilmentComplaints (kept separate from product faults), contradictions, and howToBeatThis. Null when reviews did not resolve - null means no evidence, not 'no complaints'. |