Skip to main content
Glama
Sign In

amazon-product-research-mcp

by com.webotee
OverviewDiscussionsAdmin

asin_keywords

Read-only

Reverse ASIN on Amazon (11 marketplaces): the observed head search terms where a product appeared on page 1 (organic rank, or a sponsored unit in the page), dated, organic first. Pass asins (up to 10, yours first) to compare with competitors: each keyword shows every competitor's rank, asins_on_page, and gap=true where a competitor is on page 1 and the first product is not; gaps_only=true keeps only those. Coverage is head search terms and page 1 only (the coverage block gives the counts), so a product shows fewer keywords than a full search index would. Not volume figures. The 11 Amazon marketplaces (marketplace_id; US default).

Input Schema

NameRequiredDescriptionDefault
asinNoOne ASIN. Use asins to compare.
asinsNoUp to 10 ASINs, the product first, then its competitors.
limitNoKeywords per answer (1-100).
offsetNo
gaps_onlyNoWith asins: only keywords where a competitor is on page 1 and the first product is not.
placementNoall
marketplace_idNo2 = Amazon US (default), 1 = UK, 6 = DE, 4 = CA, 5 = AU, 9 = FR, 8 = IT, 10 = ES, 7 = JP, 11 = MX, 12 = BR: the marketplaces the search-position map covers (all but US and UK since 2026-10-30, still filling in).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / marketplace_id / description
      Previous value: -"2 = Amazon US (default), 1 = Amazon UK: the marketplaces the search-position map covers."New value: +"2 = Amazon US (default), 1 = UK, 6 = DE, 4 = CA, 5 = AU, 9 = FR, 8 = IT, 10 = ES, 7 = JP, 11 = MX, 12 = BR: the marketplaces the search-position map covers (all but US and UK since 2026-10-30, still filling in)."
    • changedInput schema / properties / marketplace_id / enum
      Previous value: -[
-  2,
-  1
-]New value: +[
+  2,
+  1,
+  6,
+  4,
+  5,
+  9,
+  8,
+  10,
+  7,
+  11,
+  12
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / marketplace_id
      Added value: +{
+  "default": 2,
+  "description": "2 = Amazon US (default), 1 = Amazon UK: the marketplaces the search-position map covers.",
+  "enum": [
+    2,
+    1
+  ],
+  "type": "integer"
+}
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, it discloses real behavioral limits: coverage is head terms and page 1 only, a coverage block reports counts, results are dated and ordered organic-first, and results are not volume figures. Those are exactly the caveats an agent needs to avoid over-reading results.

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

Conciseness4/5

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

The scope and the primary usage pattern are front-loaded, and every sentence carries information. It is dense and slightly run-on (coverage caveat arrives after the comparison mechanics), but there is no filler.

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?

With no output schema, the description still names the returned fields (per-competitor rank, asins_on_page, gap), which is what an agent needs to interpret results. Minor gaps remain: offset behavior and pagination interaction with limit are not addressed.

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?

The description adds meaning the schema does not: asins ordering semantics (product first, competitors after) and the precise gap=true condition tied to gaps_only. It also explains the marketplace_id set as "the marketplaces the search-position map covers". Only offset is left unexplained in both places.

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?

"Reverse ASIN on Amazon" plus a precise scope statement ("observed head search terms where a product appeared on page 1") gives a specific verb and resource. It also pre-empts confusion with sibling tools by stating "Not volume figures", which separates it from keyword_demand/keyword_rankings style tools.

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?

It tells the agent how to enter comparison mode (pass asins, yours first) and when to narrow output (gaps_only=true). The "Not volume figures" line routes the agent away from volume-oriented siblings, but no sibling is named explicitly as an alternative.

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

All amazon-product-research-mcp toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources