Skip to main content
Glama
Sign In

Brave Search

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Web Search

web_search
Read-onlyIdempotent

General web search via the Brave index. Returns title, URL, description snippet, age, language, and site categories. Optional country, language, safesearch, and freshness filters.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "q": "best practices for machine learning"
    },
    "name": "web_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesSearch query
countNoResults to return (1-20, default 10)
offsetNo0-9 page offset (default 0)
countryNo2-letter country code (e.g., "us", "gb")
freshnessNopd (past day) | pw (past week) | pm (past month) | py (past year) | YYYY-MM-DDtoYYYY-MM-DD
safesearchNostrict | moderate | off (default moderate)
search_langNo2-letter language (e.g., "en")

Output Schema

NameRequiredDescriptionDefault
queryYesThe original search query
totalYesTotal results available for the query
alteredYesAltered query if Brave modified it, otherwise null
resultsYesArray of web search results
returnedYesNumber of results returned in this response

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "q": "best practices for machine learning"
+  },
+  {
+    "count": 15,
+    "country": "us",
+    "freshness": "pw",
+    "q": "latest AI breakthroughs",
+    "safesearch": "moderate",
+    "search_lang": "en"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "altered": {
+      "description": "Altered query if Brave modified it, otherwise null",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "query": {
+      "description": "The original search query",
+      "type": "string"
+    },
+    "results": {
+      "description": "Array of web search results",
+      "items": {
+        "properties": {
+          "age": {
+            "description": "Age of the result",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "description": {
+            "description": "Result snippet/description",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "hostname": {
+            "description": "Hostname from meta_url",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "language": {
+            "description": "Language of the result",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "page_age": {
+            "description": "Age of the page",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "thumbnail": {
+            "description": "Thumbnail image URL",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "Result title",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "Result URL",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "returned": {
+      "description": "Number of results returned in this response",
+      "type": "integer"
+    },
+    "total": {
+      "description": "Total results available for the query",
+      "type": [
+        "integer",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "query",
+    "altered",
+    "total",
+    "returned",
+    "results"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds minimal behavioral context beyond naming the Brave index and return fields. No contradictions.

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?

Two concise sentences that front-load the core purpose and immediately list return fields and optional filters. No extraneous words.

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?

The description covers purpose, return fields, and optional filters. Output schema exists for return values. Minor omission: no mention of pagination/offset, but that's documented in the schema.

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% with detailed parameter descriptions. The description mentions 'Optional country, language, safesearch, and freshness filters,' which restates schema content without adding significant new meaning.

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 it performs a 'General web search via the Brave index' and lists specific return fields (title, URL, description snippet, etc.). This distinguishes it from sibling tools like deep_research or news_search.

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?

No explicit guidance on when to use this tool versus alternatives (e.g., deep_research, news_search). The description implies general search but lacks 'when to use' or 'when not to use' instructions.

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

All Brave Search 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