Skip to main content
Glama

logimu-shopping-mcp

by com.logimu.api
OverviewDiscussionsAdmin

keyword_rankings

Read-onlyIdempotent

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 and UK. 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 account).

Input Schema

NameRequiredDescriptionDefault
countryNous (amazon.com) or uk (amazon.co.uk): the marketplaces the map covers.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. Changed2 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"Amazon US only: the map covers amazon.com search."New value: +"us (amazon.com) or uk (amazon.co.uk): the marketplaces the map covers."
    • changedInput schema / properties / country / enum
      Previous value: -[
-  "us"
-]New value: +[
+  "us",
+  "uk"
+]
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent safety, and the description adds far more: weekly sampling cadence, one US delivery ZIP, all departments, JavaScript-loaded sponsored units only counted as slots, staleness/variance, paid-plan requirement, credit cost (1, +0.5 with history), and the 2,000-call daily cap. None of that is recoverable from the annotations.

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 content is dense but nearly every clause earns its place, and the capitalized USE WHEN / NOT / COST markers make it scannable. It is still one sprawling multi-clause sentence with nested parentheticals, which costs some readability.

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?

With no output schema, the description carries the return-shape burden and does so thoroughly: field-level inventory of organic order, product facts, buy box, sponsored units, Overall Pick, result count, page_summary breakdowns and entered/left deltas. Cost, caveats, marketplace scope and error behavior are all present.

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 coverage is 100%, so both optional params are already documented in the schema, giving a baseline of 3. The description adds only modest extra meaning: that country spans Amazon US and UK, and that history returns every weekly observation plus the rank series and costs an extra half credit.

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 opening states a specific verb+resource+scope: page 1 organic order, sponsored units, Overall Pick, result count, page_summary and change deltas for a keyword on Amazon US/UK. It immediately distinguishes this snapshot from the live sibling by noting 'as Logimu last OBSERVED it' and 'same search minutes apart differs by a few products'.

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?

Uses an explicit 'USE WHEN' clause naming the questions it answers (who holds page 1, who advertises, how the page changed) and an explicit NOT list with named alternatives: serp for a live page, keywords for suggestions from a seed, product_keywords for keywords a product ranks for. It also states the free out-of-scope path (keyword_not_found).

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

All logimu-shopping-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