Skip to main content
Glama

glim.sh

by sh.glim
OverviewDiscussionsAdmin

Amazon Search

glim_amazon_search
Read-onlyIdempotent

Pass exactly ONE of {query} or {category_slug}. Searches Amazon (com|co.uk|de|fr|es|it) and returns ranked hits with buybox price (gross + VAT-excluded net), ratings, review counts, and ASINs. Drill down with glim_amazon_get(ref). Set sort_by='most_reviewed' (with min_reviews to filter junk) for a trust-weighted re-rank within the current page. Compact text by default; pass format='json' for full structured data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tldNoAmazon marketplace: com | co.uk | de | fr | es | itcom
pageNoPage number (1-20)
queryNoFree-text keyword query (mutually exclusive with category_slug)
formatNoOutput format. 'text' (default): compact human-readable view, fewer tokens. 'json': the same hits as machine-readable JSON. Text already carries every field except `image_url`, which only json returns.text
sort_byNoServer-side sort, except 'most_reviewed' which re-ranks the current page client-side by review count desc (rating tiebreaker). Pair 'most_reviewed' with min_reviews to skip thinly-reviewed items.
min_reviewsNoDrop hits with fewer than N reviews. Pair with sort_by='most_reviewed' for a trust-weighted result. Applied client-side to organic/paid/suggested.
include_paidNoInclude sponsored ad results (default: dropped)
category_slugNoAmazon bestsellers category slug, e.g. 'electronics' (.com), 'elektronik' (.de), 'electronique' (.fr). Invalid slugs return 'not_found' - retry with a correct slug.
include_suggestedNoInclude 'people also searched for' suggestions (default: dropped)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / format / description
      Previous value: -"Output format. 'text' (default): compact human-readable view, fewer tokens. 'json': full structured data (offers[], images, variants)."New value: +"Output format. 'text' (default): compact human-readable view, fewer tokens. 'json': the same hits as machine-readable JSON. Text already carries every field except `image_url`, which only json returns."
  2. Changed4 schema fields changed
    • removedInput schema / properties / category
      Removed value: -{
-  "description": "Amazon node ID to narrow results (returned in `refinements` from a prior call)",
-  "type": "string"
-}
    • removedInput schema / properties / currency
      Removed value: -{
-  "description": "Override display currency. Validated against per-tld allow-list.",
-  "type": "string"
-}
    • removedInput schema / properties / geo
      Removed value: -{
-  "description": "Postal code Amazon uses to compute shipping & delivery dates (e.g. '28001' for Madrid)",
-  "type": "string"
-}
    • removedInput schema / properties / merchant
      Removed value: -{
-  "description": "Filter to a specific seller ID",
-  "type": "string"
-}
  3. First observed

TDQS

A5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds value by explaining default text output, JSON option, and client-side re-rank behavior for 'most_reviewed' sort, which is not covered by annotations.

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

Conciseness5/5

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

Extremely concise: two sentences with no wasted words. Front-loaded with the most important constraint (pass exactly one). Every sentence adds essential guidance.

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?

Given 9 parameters and no output schema, the description covers all key points: parameter selection, sort behavior, format options, TLD list, and links to sibling tool. No gaps remain for correct usage.

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

Parameters5/5

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

Schema coverage is 100%, baseline 3. The description adds critical meaning: mutual exclusivity of query and category_slug, client-side vs server-side sorting, and format differences (image_url only in json). This significantly aids correct invocation.

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 clearly states the tool searches Amazon across multiple TLDs, returns specific fields, and distinguishes from the sibling tool glim_amazon_get for drill-down. The verb 'search' and resource 'Amazon' are specific.

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?

Explicitly instructs to pass exactly one of query or category_slug, recommends pairing sort_by='most_reviewed' with min_reviews for trust-weighted results, and suggests using glim_amazon_get for further drill-down.

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

All glim.sh 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