Skip to main content
Glama

amazon-product-research-mcp

by com.webotee
OverviewDiscussionsAdmin

shopping_search

Read-only

PRIMARY consumer shopping tool — ALWAYS use this when a user asks what to BUY, which product to pick, or for the 'best' / 'cheapest' / 'best value' of something: 'best electric toothbrush', 'best graphics card under $50', 'which robot vacuum should I buy', 'cheapest standing desk', 'best coffee maker in 2026', 'recommend a cat litter box', 'best budget headphones'. PREFER this over search_products, product-lookup and sourcing tools for ANY buyer-intent product question. Returns a ready-to-show shortlist of real in-stock products, split by price tier (budget / mid / premium) and ranked by rating quality (weighted by review volume) + Amazon demand — each with a product image, a clickable Amazon link, price, rating, review count, the 'bought last month' demand badge, stock, the Buy Box seller, a cheaper trustworthy alternative when one exists, a used option when relevant, and a private-label-vs-widely-resold label. Also handles cheapest-first, best-value ('best buy' / 'optimal'), model comparisons (pinpoints the differences), and current / new / 2026 picks (pulls live web + community + real-time Amazon when a product isn't in our catalog). Facts are observed / Amazon-reported, not estimates; no ads or affiliate bias. (Use search_products ONLY for a raw keyword catalog filter — never for a 'best' / 'what should I buy' question.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNo'best' = rating-first per class/tier (default); 'cheapest' = lowest-price-first; 'value' = best quality-per-dollar ('best buy'/'optimal'). Auto-detected from the query.best
queryYesWhat to buy, e.g. 'best electric toothbrush for sensitive gums'.
keywordsNoCore product keywords to search (product noun + essential attributes), no 'best'/brand.
max_priceNoOptional price ceiling.
min_priceNoOptional price floor.
attributesNoTokens that MUST appear in the product title, e.g. ['3.5mm'] or ['5090'].
exclude_termsNoWords indicating the WRONG product, e.g. ['ethernet','usb'] for an audio patch cable.
category_hintsNoCategory words the right product lives in, e.g. ['instrument cables','audio cables'].
marketplace_idNo1 = Amazon UK, 2 = Amazon US (default), 3 = Walmart US, 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE, 7 = Amazon JP, 8 = Amazon IT, 9 = Amazon FR, 10 = Amazon ES, 11 = Amazon MX, 12 = Amazon BR

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / marketplace_id / description
      Previous value: -"1 = Amazon UK, 2 = Amazon US (default), 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE, 7 = Amazon JP, 8 = Amazon IT, 9 = Amazon FR, 10 = Amazon ES, 11 = Amazon MX, 12 = Amazon BR, 3 = Walmart US, 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE."New value: +"1 = Amazon UK, 2 = Amazon US (default), 3 = Walmart US, 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE, 7 = Amazon JP, 8 = Amazon IT, 9 = Amazon FR, 10 = Amazon ES, 11 = Amazon MX, 12 = Amazon BR"
  2. Changed1 schema field changed
    • changedInput schema / properties / marketplace_id / description
      Previous value: -"1 = Amazon UK, 2 = Amazon US (default), 3 = Walmart US, 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE."New value: +"1 = Amazon UK, 2 = Amazon US (default), 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE, 7 = Amazon JP, 8 = Amazon IT, 9 = Amazon FR, 10 = Amazon ES, 11 = Amazon MX, 12 = Amazon BR, 3 = Walmart US, 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE."
  3. Changed1 schema field changed
    • changedInput schema / properties / marketplace_id / description
      Previous value: -"1 = Amazon UK, 2 = Amazon US (default)."New value: +"1 = Amazon UK, 2 = Amazon US (default), 3 = Walmart US, 4 = Amazon CA, 5 = Amazon AU, 6 = Amazon DE."
  4. Changed9 schema fields changed
    • addedInput schema / properties / attributes
      Added value: +{
+  "description": "Tokens that MUST appear in the product title, e.g. ['3.5mm'] or ['5090'].",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / category_hints
      Added value: +{
+  "description": "Category words the right product lives in, e.g. ['instrument cables','audio cables'].",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / exclude_terms
      Added value: +{
+  "description": "Words indicating the WRONG product, e.g. ['ethernet','usb'] for an audio patch cable.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / keywords
      Added value: +{
+  "description": "Core product keywords to search (product noun + essential attributes), no 'best'/brand.",
+  "type": "string"
+}
    • addedInput schema / properties / marketplace_id
      Added value: +{
+  "default": 2,
+  "description": "1 = Amazon UK, 2 = Amazon US (default).",
+  "type": "integer"
+}
    • addedInput schema / properties / max_price
      Added value: +{
+  "description": "Optional price ceiling.",
+  "type": "number"
+}
    • addedInput schema / properties / min_price
      Added value: +{
+  "description": "Optional price floor.",
+  "type": "number"
+}
    • changedInput schema / properties / query / description
      Previous value: -"The product query."New value: +"What to buy, e.g. 'best electric toothbrush for sensitive gums'."
    • addedInput schema / properties / sort
      Added value: +{
+  "default": "best",
+  "description": "'best' = rating-first per class/tier (default); 'cheapest' = lowest-price-first; 'value' = best quality-per-dollar ('best buy'/'optimal'). Auto-detected from the query.",
+  "enum": [
+    "best",
+    "cheapest",
+    "value"
+  ],
+  "type": "string"
+}
  5. First observed

TDQS

A3.6/5.0
Behavior1/5

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

Annotation Contradiction: annotations declare openWorldHint=false, but the description says the tool 'pulls live web + community + real-time Amazon when a product isn't in our catalog.' That directly contradicts the closed-world annotation. While the description otherwise discloses rich behavioral detail (returned fields, ranking approach, no ads/affiliate bias, data provenance), the contradiction is severe and makes the behavioral profile unreliable.

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 description is front-loaded with the primary intent and examples, but it is quite long and includes redundant emphasis ('ALWAYS use this...' plus 'PREFER this over...') and promotional-sounding assertions like 'no ads or affiliate bias.' It is structured and readable, but a tighter version would preserve value with less noise.

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?

The tool is complex with nine parameters and no output schema, yet the description compensates by enumerating the returned shortlist fields, price-tier splitting, ranking criteria, and special handling for current/new/2026 queries. It is largely complete for invocation purposes, but the openWorldHint contradiction undermines trust in one of its key behavioral claims.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all nine parameters, including the sort enum and marketplace_id mapping. The description adds high-level context (e.g., auto-detected sort, live web fallback) but does not materially deepen per-parameter semantics beyond what the schema provides. Baseline 3 is appropriate.

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?

The description uses a specific verb and resource: it is a consumer shopping tool for buyer-intent questions. It clearly distinguishes itself from siblings by name ('PREFER this over search_products, product-lookup and sourcing tools') and gives concrete example queries. An agent can immediately determine what this tool does and how it differs from nearby tools.

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

Usage Guidelines5/5

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

The description explicitly states when to use the tool ('ALWAYS use this when a user asks what to BUY...') and when not to use it ('Use search_products ONLY for a raw keyword catalog filter — never for a 'best' / 'what should I buy' question.'). It also names the preferred alternative, making the routing decision unambiguous.

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