Skip to main content
Glama
Sign In

Nexscope

by io.github.nexscope
OverviewDiscussionsAdmin

Amazon Search By Image

nexscope_amazon_search_by_image
Read-only

Perform image-based visual product search on Amazon across 8 marketplaces. Use an image URL to find visually similar products, with optional Nexscope enrichment for sales data. Triggered when users mention Amazon image search, Amazon visual search, find similar products on Amazon, reverse image lookup Amazon, Amazon search by photo, or competitor image search. Even if the user does not explicitly mention "image search," this skill should be triggered whenever a user provides an image URL and wants to find visually matching or similar products on Amazon.

Input Schema

NameRequiredDescriptionDefault
sortNoSort by price, rating, or rating count. Values: default, price-asc-rank, price-desc-rank, rating-asc-rank, rating-desc-rank, ratings-asc-rank, and ratings-desc-rank
topNNoMaximum matches in matches mode, clamped to 1-100; default 20.
imageUrlYesValid, publicly accessible image URL (maximum 1,000 characters)
deliveryZipNoDelivery postal code or city within the selected marketplace. If omitted, the marketplace default is used. Maximum 1,000 characters. Defaults: United States=10001, United Kingdom=EC1A 1BB, Germany=10115, France=75001, Italy=00100, Spain=28001, Japan=100-0001, and India=110034
amazonDomainYesAmazon marketplace. Supported domains: United States (amazon.com), United Kingdom (amazon.co.uk), Germany (amazon.de), France (amazon.fr), Italy (amazon.it), Spain (amazon.es), Japan (amazon.co.jp), and India (amazon.in). Default: amazon.com
responseFormatNoraw (default) preserves the provider result; matches forces enrichment and returns ranked matches.
countryOrAreaCodeNoDestination country or region code for cross-border delivery, such as CN, JP, KR, TW, HK, MO, SG, TH, VN, PH, or MY. Do not provide this together with deliveryZip. Amazon India does not support cross-border destination settings. Maximum 1,000 characters
aggregateByKeepaDataNoWhether to enrich results with Nexscope data such as sales rank, monthly sales, FBA fees, and dimensions

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / responseFormat
      Added value: +{
+  "description": "raw (default) preserves the provider result; matches forces enrichment and returns ranked matches.",
+  "example": "raw",
+  "type": "string"
+}
    • addedInput schema / properties / topN
      Added value: +{
+  "description": "Maximum matches in matches mode, clamped to 1-100; default 20.",
+  "example": 20,
+  "type": "integer"
+}
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds non-obvious context: multi-marketplace coverage and the optional Nexscope enrichment for sales data, though it says nothing about latency, rate limits, or what the response actually contains in raw vs matches mode.

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 purpose and scope are front-loaded, but the middle sentence is a stuffed list of near-synonymous trigger phrases ('Amazon image search, Amazon visual search, find similar products on Amazon, reverse image lookup Amazon, Amazon search by photo') that consumes tokens without adding discriminating information.

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 an 8-parameter tool with no output schema, the definition covers purpose, marketplace scope, and the enrichment option adequately. The remaining gap is that it never characterizes results (what a 'match' contains, ordering behavior in raw vs matches mode), which the absent output schema would otherwise excuse.

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 every parameter including sort, topN, deliveryZip, countryOrAreaCode and responseFormat is already documented. The description restates the image-URL input and the enrichment toggle but adds no syntax, mutual-exclusion, or format detail beyond the schema, so the baseline of 3 applies.

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 names a specific verb and resource ('image-based visual product search on Amazon') and bounds the scope to 8 marketplaces, which separates it cleanly from keyword siblings like nexscope_amazon_search and from non-Amazon image search tools such as nexscope_1688_search_by_image.

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 gives explicit trigger conditions, including a broadened rule ('even if the user does not explicitly mention image search... whenever a user provides an image URL'), which is genuinely useful routing guidance. It stops short of naming when NOT to use it or pointing to alternative siblings for other marketplaces or keyword-based flows.

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

All Nexscope 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