Skip to main content
Glama

google: Web search results

google_search
Read-only

Web search results. Google web results for a query, 20 per page, up to 6 pages. Ranking can differ from a signed-out search on google.com. A failed attempt returns upstream_unavailable and is not charged. Costs 1 credit.

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
pageNo1-based page number, up to 6. 20 results per page.
queryYes
regionNoTwo-letter country code (US, GB, DE, IN, ...) or a Google geo criteria idUS
date_postedNoNot currently supported; any value returns `invalid_request`.
cache_max_ageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / date_posted / description
      Added value: +"Not currently supported; any value returns `invalid_request`."
    • changedInput schema / properties / page / description
      Previous value: -"1-based page number"New value: +"1-based page number, up to 6. 20 results per page."
  2. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Adds substantial behavior beyond the readOnly/openWorld annotations: result volume (20 per page, up to 6 pages), that ranking may differ from signed-out google.com, that failure returns `upstream_unavailable` and is not charged, and the 1-credit cost. Cost and failure semantics are exactly the kind of context annotations cannot convey.

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?

Front-loaded and compact at four short sentences, each carrying real information. Minor redundancy between 'Web search results' and 'Google web results for a query,' but no padding.

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?

No output schema and a simple 5-parameter read tool; the description covers pagination, ranking variance, error handling, and cost. The main gap is the unexplained `cache_max_age` parameter, which matters for a tool with caching behavior.

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 60%, so the baseline is 3. The description repeats pagination facts already in the schema and does not mention the undocumented `cache_max_age` parameter at all, so it does not fully compensate for the coverage gap.

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?

States a specific verb+resource: 'Google web results for a query.' This distinguishes it implicitly from vertical siblings like google_news or google_shopping by scoping to general web results, but it does not name those alternatives explicitly, leaving routing to inference.

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—an agent infers general web search from 'web results for a query.' There is no explicit when-to-use versus google_news, google_jobs, or google_shopping, and no stated exclusions.

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.