Skip to main content
Glama

TokConnect: TikTok Research

One TikTok Shop product

product
Read-onlyIdempotent

Everything about one TikTok Shop product (id = product id or a Shop product link). Live from TikTok: page (price, SKUs and stock, rating, shop, and sold = TikTok's displayed lifetime units), reviews, related products, page videos. [Shop Analytics, any market via region]: sales, trend (daily), creators, video_sales, skus, analysis (highlights and attributes), conversion (creators promoting it and the share who sold), review_insights (complaints, praise, use cases; by_sku splits by variant). Examples: {"id":"1732052189676081387","method":"trend","window":"90d"}, {"ids":["1729...","1731..."],"method":"sales","region":"DE"}.

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": "product"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoProduct id (products[].id) or a TikTok Shop product link.
endNoShop Analytics methods: custom range end, YYYY-MM-DD (capped at the last complete day).
idsNomethod=sales only: up to 20 product ids in one call.
pageNomethod=reviews: jump to this page (1-100).
sortNomethod=reviews: recommended (default) or newest.
limitNoResults per page. reviews max 5, related max 30, videos max 20; Shop Analytics methods max 100. Values above a method's maximum are lowered and reported in notes.
starsNomethod=reviews: star filter when filter=all.
startNoShop Analytics methods: custom range start, YYYY-MM-DD.
by_skuNomethod=review_insights: split insights by SKU.
cursorNoPaging: pass the next value from the previous response unchanged. Omit on the first page.
detailNocompact (default) returns the useful fields; full adds the full raw record (large).compact
filterNomethod=reviews: all (default), with_media or verified.
methodNoWhat to get. page: live price, SKUs and stock, sold, rating, shop | reviews: public reviews | related: products TikTok shows as related | videos: the videos on the product page (first page only) | sales [Shop Analytics, 2 credits]: revenue, units, video/LIVE/showcase split, creator count, conversion (ids: up to 20 products) | trend [Shop Analytics, 2 credits]: daily revenue and units (up to ~13 months) | creators [Shop Analytics, 2 credits]: creators selling it, ranked, with revenue | video_sales [Shop Analytics, 2 credits]: videos selling it, with revenue | skus [Shop Analytics, 2 credits]: sales by variant (SKU) | analysis [Shop Analytics, 2 credits]: selling-point highlights and attributes Shop Analytics extracts for the product | conversion [Shop Analytics, 2 credits]: how many creators promote it and what share of them made sales | review_insights [Shop Analytics, 2 credits]: AI summary of reviews: pain points, praise, use cases (by_sku splits by variant)page
regionNoMarket as an ISO country code, default US. Shop Analytics methods: sales data for that market, amounts in its currency. Live methods that take it (search, video detail, creator posts, Shop pages): TikTok as seen in that market where TikTok serves it. Core: US, GB, DE, FR, ES, JP, TH, VN, ID, MY, PH, BR, MX. Extended: PL, IT, NL, IE. Other countries are refused. See shop_regions.
windowNoShop Analytics methods: date range ending at the last complete day (about 2 days ago). Default 30d. Use start/end for a custom range.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / method / description
      Previous value: -"What to get. page: live price, SKUs and stock, sold, rating, shop | reviews: public reviews | related: products TikTok shows as related | videos: the videos on the product page (first page only) | sales [Shop Analytics]: revenue, units, video/LIVE/showcase split, creator count, conversion (ids: up to 20 products) | trend [Shop Analytics]: daily revenue and units (up to ~13 months) | creators [Shop Analytics]: creators selling it, ranked, with revenue | video_sales [Shop Analytics]: videos selling it, with revenue | skus [Shop Analytics]: sales by variant (SKU) | analysis [Shop Analytics]: selling-point highlights and attributes Shop Analytics extracts for the product | conversion [Shop Analytics]: how many creators promote it and what share of them made sales | review_insights [Shop Analytics]: AI summary of reviews: pain points, praise, use cases (by_sku splits by variant)"New value: +"What to get. page: live price, SKUs and stock, sold, rating, shop | reviews: public reviews | related: products TikTok shows as related | videos: the videos on the product page (first page only) | sales [Shop Analytics, 2 credits]: revenue, units, video/LIVE/showcase split, creator count, conversion (ids: up to 20 products) | trend [Shop Analytics, 2 credits]: daily revenue and units (up to ~13 months) | creators [Shop Analytics, 2 credits]: creators selling it, ranked, with revenue | video_sales [Shop Analytics, 2 credits]: videos selling it, with revenue | skus [Shop Analytics, 2 credits]: sales by variant (SKU) | analysis [Shop Analytics, 2 credits]: selling-point highlights and attributes Shop Analytics extracts for the product | conversion [Shop Analytics, 2 credits]: how many creators promote it and what share of them made sales | review_insights [Shop Analytics, 2 credits]: AI summary of reviews: pain points, praise, use cases (by_sku splits by variant)"
  2. Changed2 schema fields changed
    • changedInput schema / properties / detail / description
      Previous value: -"compact (default) returns the useful fields; full adds the raw upstream payload (large)."New value: +"compact (default) returns the useful fields; full adds the full raw record (large)."
    • changedInput schema / properties / method / description
      Previous value: -"What to get. page: live price, SKUs and stock, sold, rating, shop | reviews: public reviews | related: products TikTok shows as related | videos: the videos on the product page (first page only) | sales [Shop Analytics]: revenue, units, video/LIVE/showcase split, creator count, conversion (ids: up to 20 products) | trend [Shop Analytics]: daily revenue and units (up to ~13 months) | creators [Shop Analytics]: creators selling it, ranked, with revenue | video_sales [Shop Analytics]: videos selling it, with revenue | skus [Shop Analytics]: sales by variant (SKU) | analysis [Shop Analytics]: selling-point highlights and attributes the source extracts for the product | conversion [Shop Analytics]: how many creators promote it and what share of them made sales | review_insights [Shop Analytics]: AI summary of reviews: pain points, praise, use cases (by_sku splits by variant)"New value: +"What to get. page: live price, SKUs and stock, sold, rating, shop | reviews: public reviews | related: products TikTok shows as related | videos: the videos on the product page (first page only) | sales [Shop Analytics]: revenue, units, video/LIVE/showcase split, creator count, conversion (ids: up to 20 products) | trend [Shop Analytics]: daily revenue and units (up to ~13 months) | creators [Shop Analytics]: creators selling it, ranked, with revenue | video_sales [Shop Analytics]: videos selling it, with revenue | skus [Shop Analytics]: sales by variant (SKU) | analysis [Shop Analytics]: selling-point highlights and attributes Shop Analytics extracts for the product | conversion [Shop Analytics]: how many creators promote it and what share of them made sales | review_insights [Shop Analytics]: AI summary of reviews: pain points, praise, use cases (by_sku splits by variant)"
  3. Changed1 schema field changed
    • changedInput schema / properties / region / description
      Previous value: -"Shop Analytics methods: market as an ISO country code, default US. Core: US, GB, DE, FR, ES, JP, TH, VN, ID, MY, PH, BR, MX. Extended: PL, IT, NL, IE. Other countries are refused. Amounts are in the market's currency. See shop_regions."New value: +"Market as an ISO country code, default US. Shop Analytics methods: sales data for that market, amounts in its currency. Live methods that take it (search, video detail, creator posts, Shop pages): TikTok as seen in that market where TikTok serves it. Core: US, GB, DE, FR, ES, JP, TH, VN, ID, MY, PH, BR, MX. Extended: PL, IT, NL, IE. Other countries are refused. See shop_regions."
  4. Changed3 schema fields changed
    • changedInput schema / properties / method / description
      Previous value: -"What to get. page: live price, SKUs and stock, sold, rating, shop | reviews: public reviews | related: products TikTok shows as related | videos: the videos on the product page (first page only) | sales [Shop Analytics]: revenue, units, video/LIVE/showcase split, creator count, conversion (ids: up to 20 products) | trend [Shop Analytics]: daily revenue and units (up to ~13 months) | creators [Shop Analytics]: creators selling it, ranked, with revenue | video_sales [Shop Analytics]: videos selling it, with revenue | skus [Shop Analytics]: sales by variant (SKU) | review_insights [Shop Analytics]: AI summary of reviews: pain points, praise, use cases (by_sku splits by variant)"New value: +"What to get. page: live price, SKUs and stock, sold, rating, shop | reviews: public reviews | related: products TikTok shows as related | videos: the videos on the product page (first page only) | sales [Shop Analytics]: revenue, units, video/LIVE/showcase split, creator count, conversion (ids: up to 20 products) | trend [Shop Analytics]: daily revenue and units (up to ~13 months) | creators [Shop Analytics]: creators selling it, ranked, with revenue | video_sales [Shop Analytics]: videos selling it, with revenue | skus [Shop Analytics]: sales by variant (SKU) | analysis [Shop Analytics]: selling-point highlights and attributes the source extracts for the product | conversion [Shop Analytics]: how many creators promote it and what share of them made sales | review_insights [Shop Analytics]: AI summary of reviews: pain points, praise, use cases (by_sku splits by variant)"
    • changedInput schema / properties / method / enum
      Previous value: -[
      -  "page",
      -  "reviews",
      -  "related",
      -  "videos",
      -  "sales",
      -  "trend",
      -  "creators",
      -  "video_sales",
      -  "skus",
      -  "review_insights"
      -]New value: +[
      +  "page",
      +  "reviews",
      +  "related",
      +  "videos",
      +  "sales",
      +  "trend",
      +  "creators",
      +  "video_sales",
      +  "skus",
      +  "analysis",
      +  "conversion",
      +  "review_insights"
      +]
    • addedInput schema / properties / region
      Added value: +{
      +  "description": "Shop Analytics methods: market as an ISO country code, default US. Core: US, GB, DE, FR, ES, JP, TH, VN, ID, MY, PH, BR, MX. Extended: PL, IT, NL, IE. Other countries are refused. Amounts are in the market's currency. See shop_regions.",
      +  "maxLength": 2048,
      +  "type": "string"
      +}
  5. Added

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only/idempotent safety, so this adds genuinely new behavioral facts: Shop Analytics calls cost 2 credits, region values outside the listed core/extended set are refused, limit values above a method's cap are silently lowered and reported in notes, videos returns only the first page, and trend reaches ~13 months ending at the last complete day. These are exactly the operational constraints an agent needs before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The lead sentence and the examples are well-placed and earn their space, but the long middle list of methods restates the method enum description almost verbatim, giving no credit beyond structured data. Front-loading is good; total length is inflated by that duplication.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, twelve-method tool with an output schema and full schema coverage, the description covers cost, region eligibility, window semantics, and paging well enough to call correctly. It could say a bit more about which methods return paginated results and how cursor interacts with page, but nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, but the description adds working call shapes ({"id":"...","method":"trend","window":"90d"} and a multi-id sales example) and clarifies that id accepts a full Shop product link, which the schema only states tersely. It does not, however, explain the interaction between window and start/end beyond 'use start/end for a custom range'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: 'Everything about one TikTok Shop product (id = product id or a Shop product link)', then enumerates the twelve method values, so an agent can tell this apart from shop-level or ranking siblings. The scope statement ('Live from TikTok' vs '[Shop Analytics, any market via region]') makes the two data planes explicit up front.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The per-method annotations effectively tell the agent which method to pick for reviews, variants, creators, video sales, or AI review summaries, and it names the cost (2 credits) and the market override via region. It stops short of saying when to use this tool instead of a sibling such as shop or product_top_selling, and there are no explicit when-not conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources