Skip to main content
Glama

Google Search

google_search
Read-onlyIdempotent

Searches Google web results and returns up to 20 organic results (title, url, snippet, position) for a query, localized by country and language; page gives later results. Use it to find pages and sources. It does not return page contents (use scrape_url on a result url), ads or other result blocks, and is not for news, products or local places (use search_news, google_shopping_prices or google_maps_places). A search with no matches is charged; errors are not. Required: query.

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_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoZero-based results page, integer 0-100: 0 is the first page, 1 the second, e.g. 1. Omit for the first page; each page is a separate charged call.
queryYesSearch text, 1-500 characters, e.g. "espresso machine reviews"; operators such as site:example.com work.
countryNoTwo-letter country code that localizes results, e.g. "it" for Italy or "gb" for the United Kingdom. Omit for the source default, us.
resultsNoMaximum organic results returned, integer 1-20, default 10, e.g. 5.
languageNoTwo-letter language code for the results, e.g. "en" or "it". Omit for the source default, en.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"Two-letter country code used to localize results."New value: +"Two-letter country code that localizes results, e.g. \"it\" for Italy or \"gb\" for the United Kingdom. Omit for the source default, us."
    • changedInput schema / properties / language / description
      Previous value: -"Two-letter language code for result text."New value: +"Two-letter language code for the results, e.g. \"en\" or \"it\". Omit for the source default, en."
    • changedInput schema / properties / page / description
      Previous value: -"Zero-based search result page number."New value: +"Zero-based results page, integer 0-100: 0 is the first page, 1 the second, e.g. 1. Omit for the first page; each page is a separate charged call."
    • changedInput schema / properties / query / description
      Previous value: -"Search query to submit to the web search engine."New value: +"Search text, 1-500 characters, e.g. \"espresso machine reviews\"; operators such as site:example.com work."
    • changedInput schema / properties / results / description
      Previous value: -"Maximum number of organic results to return."New value: +"Maximum organic results returned, integer 1-20, default 10, e.g. 5."
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only, open-world and idempotent, so the safety profile is covered; the description goes further with the exact result shape and cap, the pagination behavior of the page param, and the billing rule ('a search with no matches is charged; errors are not'). That cost/pagination/return-shape context is real value beyond structured fields.

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?

Purpose is front-loaded in the first clause, and every clause carries weight: output shape, pagination, exclusions with alternatives, billing, required param. It is a dense multi-clause run-on with semicolons rather than clean sentences, which slightly hurts scanability but not information density.

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?

There is no output schema, and the description compensates by enumerating the returned fields (title, url, snippet, position) and the 20-result ceiling. Combined with pagination, cost behavior, localization defaults and explicit sibling routing, 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.

Parameters3/5

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

Schema coverage is 100%, so every parameter is already documented in detail (page range and per-page charge, query length and operator support, country/language enums and defaults). The description adds only a light gloss — 'localized by country and language' and 'page gives later results' — which does not meaningfully exceed the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and resource ('Searches Google web results') plus the exact scope of output ('up to 20 organic results (title, url, snippet, position)'), localized by country and language. It names what it is not — news, products, local places, page contents — so an agent can distinguish it from search_news, google_shopping_prices, google_maps_places and scrape_url without reading the schema.

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 says what to use it for ('find pages and sources'), what it does not return, and routes each exclusion to a named alternative sibling (scrape_url, search_news, google_shopping_prices, google_maps_places). Both the positive and negative selection conditions are spelled out.

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.

Resources