Skip to main content
Glama
Sign In
logimu-shopping-mcp

logimu-shopping-mcp

by ncosic
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

keyword_rankings

Read-onlyIdempotent

Retrieve observed Amazon US page 1 results for a search term, including organic product rankings, sponsored placements, brands, sellers, and changes since the prior weekly observation.

Instructions

Page 1 of Amazon US search for a keyword, as Logimu last OBSERVED it (head search terms taken from Amazon's own autocomplete, each observed about once a week, all departments, one US delivery ZIP): the organic order with product facts (title, brand, price, rating) and each product's latest observed buy box (seller, AMZ / FBA / FBM, other sellers), the sponsored units present in the page HTML (Sponsored Brands banners and videos, server-rendered Sponsored Products; ones Amazon loads later by JavaScript are counted as slots only), the Overall Pick (Amazon's Choice) holder, Amazon's result count, page_summary (organic slots by brand and by buy-box seller, Amazon's own buy boxes, FBA / FBM, Sponsored Brands units by brand) and the products that entered or left page 1 since the previous observation, all dated. history=true adds every weekly observation and the rank series of the page's products. USE WHEN the user asks which products, brands or sellers hold page 1 for a search term, who advertises on it, or how the page changed. Amazon US only. NOT volume figures (Amazon publishes none for search terms and none is implied) and NOT live: a dated weekly sample, and the same search minutes apart differs by a few products - for a live page use the serp tool, for what Amazon suggests for a seed the keywords tool, for the keywords a product shows up for product_keywords. A keyword outside the observed set is free (keyword_not_found). COST: paid plan required (listed only for keys on a paid plan); 1 credit (+0.5 with history when more than one observation exists). Counts against the derived daily cap (default 2,000 calls per key).

Input Schema

NameRequiredDescriptionDefault
countryNoAmazon US only: the map covers amazon.com search.us
historyNoAlso return every weekly observation and the products' rank series; +0.5 credit when more than one exists.
keywordYesA search term, e.g. 'micro sd card 128gb high endurance' (case-insensitive).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.8.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds substantial context beyond them: paid-plan gating, 1 credit (+0.5 with history), the 2,000-call daily cap, the dated weekly-sample nature versus live results, and the free keyword_not_found behavior for out-of-set terms.

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?

It is front-loaded with the core purpose and the USE WHEN / NOT / COST routing appears in a sensible order. The cost/freshness detail is dense but every clause carries routing or behavioral information; the single unbroken paragraph is the only real structural weakness.

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

Completeness5/5

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

For a no-output-schema tool with a rich payload, the description enumerates what is returned (organic order, buy box, sponsored units, page_summary, entrants/leavers, history series), the cost model, the data-freshness caveat and the sibling alternatives. An agent has everything needed to call it correctly.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains that history=true returns every weekly observation plus rank series and carries a cost implication, and confirms country is US-only against the amazon.com map. The keyword parameter's semantics are left entirely to the schema example.

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 states a precise verb+resource: the observed page-1 organic order for a keyword, with product facts, buy box, sponsored units, Overall Pick, result count and page_summary. It is unmistakably distinguishable from siblings like serp, keywords and product_keywords, which it names directly.

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?

Explicit routing is provided: 'USE WHEN the user asks which products, brands or sellers hold page 1...' plus exclusions for volume figures, live pages, autocomplete suggestions and product-keyword mapping, each with the correct alternative tool (serp, keywords, product_keywords). Nothing is left to inference.

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

Deploy Server

Other Tools