Skip to main content
Glama

google: Google Shopping results

google_shopping
Read-only

Google Shopping results. Shopping listings for a query: title, price, currency and merchant. url and availability are null because the listing page does not carry them. Slower than most endpoints, often 20 seconds or more. A failed attempt returns upstream_unavailable and is not charged. Costs 5 credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "google_shopping"
  }
}

Input Schema

NameRequiredDescriptionDefault
glNoTwo-letter country code Google should bias results toward.
hlNoHost language for the results page, e.g. "en", "de". Defaults to "en".en
tbsNoNot currently supported; any value returns `invalid_request`.
tldNoGoogle marketplace TLD. One of: com, co.uk, ca, de, es, fr, it, co.jp, in, cn, com.sg, com.mx, ae, com.br, nl, com.au, com.tr, sa, se, pl. Defaults to "com".com
uuleNoNot currently supported; any value returns `invalid_request`.
queryYesSearch query
startNoNot currently supported; any value returns `invalid_request`.
country_codeNoTwo-letter country code. Sets `gl` when `gl` is not given.
cache_max_ageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / start / description
      Previous value: -"0-based result offset."New value: +"Not currently supported; any value returns `invalid_request`."
    • changedInput schema / properties / tbs / description
      Previous value: -"Time filter: hour/day/week/month/year, as Google's own `qdr` code."New value: +"Not currently supported; any value returns `invalid_request`."
    • changedInput schema / properties / uule / description
      Previous value: -"Encoded Google location string for precise geo-targeting."New value: +"Not currently supported; any value returns `invalid_request`."
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses the return payload shape (title, price, currency, merchant), that url and availability are always null for this listing type, that the call often takes 20+ seconds, that upstream failures return upstream_unavailable and are not billed, and that each call costs 5 credits. That is unusually rich operational context an agent cannot get from the annotations or schema.

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?

Four short sentences, front-loaded with what the tool returns, then caveats on missing fields, latency, failure behavior and cost. No sentence is redundant and each adds a distinct fact.

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 a 9-parameter, mutation-free search tool with no output schema, the description covers returns, null fields, latency, failure semantics and pricing. The only minor omissions are cache_max_age behavior and pagination, though the schema already marks start as unsupported, so the agent has enough to call it correctly.

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 89% and the schema itself documents gl, hl, tld, country_code and even flags tbs/uule/start as unsupported. The description adds no parameter-level meaning, only the note that url/availability are null in the response, which is not a parameter. Baseline 3 is appropriate when the schema carries the semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource ('Google Shopping results') and specifies exactly what listings contain: title, price, currency and merchant. That is a specific verb-plus-resource statement and a reader can tell it apart from google_search by the shopping-listing payload. It stops short of naming a sibling outright, so it is clear rather than sharply differentiated.

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

Usage Guidelines3/5

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

Usage is only implied: 'Shopping listings for a query' tells an agent this is for product/price lookups, and the latency warning hints at when to prefer something faster. There is no explicit statement of when-not-to-use it or which alternative to pick (google_search, amazon_search, walmart_search) for non-shopping or faster queries.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.