Skip to main content
Glama

Search the web

browser_search
Read-only

Search the web via a search API and return numbered titles, URLs, and snippets. Use it to find which site has what a task needs before opening the page to verify details.

Instructions

Search the web without the browser (a search API, so no bot check): a numbered list of title, address and snippet. Use it to find which site has what the task needs, then open the result with browser_navigate; a snippet can be out of date, so check a value on the page itself.

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
siteNoOnly results from this site, e.g. "en.wikipedia.org"
queryYesWords to search the web for
max_resultsNoDefault 8

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld and non-destructive, so the safety profile is covered. The description still adds real value beyond them: it discloses that this is a search API with no bot-check friction, that results come back as a numbered list of three fields, and that snippets may be out of date and should be verified on-page.

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?

Two sentences with essentially no filler, and the key distinction (no browser, no bot check) plus the return shape lead the definition. The trailing staleness caveat is well placed since it changes how the agent consumes results.

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?

There is no output schema, so the description usefully names the returned fields and their numbering. Combined with the follow-up workflow advice, an agent has what it needs to call and then act on results; only minor details like result ranking or failure behavior are absent.

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 100%, so query, site and max_results are fully documented in the schema, including the default of 8 and the 1-10 cap. The description adds no syntax or scoping detail about these parameters, so the baseline 3 applies.

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") plus the mechanism (a search API, not a browser, so no bot check) and the return shape (numbered list of title, address and snippet). This clearly separates it from the browser_* siblings, which drive a live page rather than query a search API.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: use this to discover which site has what the task needs, then open the result with browser_navigate, and re-verify snippets on the page because they can be stale. It lacks an explicit when-not-to-use case (e.g. when the target URL is already known and browser_navigate alone suffices), so it falls just short of a 5.

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