Skip to main content
Glama

Web Search

search
Read-only

Search the web with SERP, AI synthesis, or both. Returns, by mode: serp the organic results (title, url, snippet, position, and the displayed link, date and sitelinks where Google shows them) with the page's People also ask questions, related searches, answer box, top stories and knowledge graph; ai a written answer with the URLs it cites; deep both. Use for current facts, news and finding pages. To read one page in full use scrape; for a report built from many sources use research. Cost: serp 1 credit, ai 2 credits, deep 3 credits, charged only when a call succeeds.

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": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoMode: serp (Raw Google SERP results), ai (AI-synthesized answers with citations), deep (SERP + AI synthesis combined).
queryYesThe search query.
countryNoISO country code of the Google results (serp and deep modes).us
freshnessNoOnly sources from this window, in every mode.any
num_resultsNoMaximum number of organic results (serp and deep modes).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, and the description goes well beyond them: it discloses the exact payload returned per mode (organic results, People also ask, related searches, answer box, top stories, knowledge graph, cited URLs) and a per-mode credit price with the key billing rule that charges occur 'only when a call succeeds.' That billing and return-shape detail cannot be derived from any structured field.

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 with purpose and modes, then returns, usage, alternatives and cost. Every sentence carries information, though the second sentence packs a long enumeration of SERP sub-fields that is dense to parse in one pass.

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, so the per-mode return description is essential and present. Combined with cost disclosure, mode applicability hints and sibling routing, an agent has everything needed to select a mode and call the tool correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents mode, country, freshness and num_results including their mode applicability. The description adds marginal meaning by tying the mode choice to concrete output contents (e.g., 'ai a written answer with the URLs it cites'), which helps an agent pick a mode, but it does not add syntax or format detail beyond the schema.

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 ('Search the web') and immediately enumerates the three operating modes (SERP, AI synthesis, both), so an agent knows exactly what capability it is selecting. The description also distinguishes this tool from scrape and research by name, preventing confusion among the three search-adjacent siblings.

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?

Provides explicit positive guidance ('current facts, news and finding pages') and explicit negative routing: 'To read one page in full use scrape; for a report built from many sources use research.' Both conditions that select an alternative are spelled out, leaving nothing to inference.

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.