Skip to main content
Glama

browser_search

Searches the web in a real Chromium browser and returns result links, handling JavaScript and filtering ads as the first step of a browser-driven OSINT investigation.

Instructions

Search the web in a real Chromium browser and return result links.

Engines: auto (DuckDuckGo -> Bing -> Brave), duckduckgo, bing, brave. Handles JS, decodes DuckDuckGo redirect links, filters ads. Use this as the first step of a browser-driven OSINT investigation.

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": "browser_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
engineNoauto

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose useful traits beyond the schema: an engine fallback chain (DuckDuckGo -> Bing -> Brave), JS execution, redirect-link decoding, and ad filtering. It says nothing about rate limiting, bot-blocking/CAPTCHA risk, timeouts, or how many results typical runs yield, so mutation-free operation is only partly characterized.

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?

Four short sentences, front-loaded with the core action and followed by operational detail. No padding or repetition, and the engine list is compactly formatted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return values are described at a high level ("return result links") and there is no output schema, so the description should say more about result shape, ranking, or failure behavior to be fully self-sufficient. For a 3-parameter search tool it is serviceable but leaves meaningful gaps around limits and error conditions.

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 0%, so the description must compensate. It partially does: the listed engine values (auto, duckduckgo, bing, brave) effectively define the `engine` parameter's accepted options and the fallback semantics of "auto," which the schema does not. The `limit` parameter and any guidance on `query` construction are left entirely undocumented.

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 gives a specific verb and resource ("Search the web") plus a concrete differentiator: it runs "in a real Chromium browser" and "handles JS," which implicitly separates it from an HTTP-only search sibling. It stops short of naming the sibling it differs from, so the contrast is inferred rather than stated.

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?

"Use this as the first step of a browser-driven OSINT investigation" gives a real usage context and implies a position in a workflow. However, there is no explicit when-not guidance, no mention of when a plain web search would be preferable, and no prerequisite or cost warnings.

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