Skip to main content
Glama

聚搜GO Jusou

联网搜索

web_search
Read-only

用 聚搜GO 联网搜索,返回标题、链接、摘要。想用某家就指定 engine;不指定则用默认引擎(anysearch);想对比就传 engines(几家同时搜,各自扣分)。怎么选:exa:英文/语义找资料、找同类网页;serpapi:Google 搜索结果,参数与返回同 SerpApi 官方;tavily:给 Agent 的干净结果、新闻;serper:Google 搜索结果,速度快;anysearch:中文与通用网页、垂直领域 tag;brave:海外网页、给 AI 的正文上下文;bocha:国内中文网页与长摘要;baidu:国内中文网页与 AI 速答。扣分 1–4 积分/次(按引擎与档位,depth=advanced/deep 档位更高;Exa 超过 10 条每多 10 条加收,各档与加价用 list_engines 查);失败不扣分。结果末尾有一句本次扣分与剩余积分。

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": "web_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNo搜索深度,默认 basic;各引擎支持:exa basic/advanced/deep;serpapi basic;tavily basic/advanced;serper basic;anysearch basic;brave basic/advanced;bocha basic;baidu basic/advanced
mergeNo多引擎时合并去重
queryYes搜索词
engineNo指定一个引擎;不填则用默认引擎(和 engines 二选一)
enginesNo同时搜几个引擎,各自扣分
languageNo结果语言,如 zh / en(引擎支持时生效)
time_rangeNo
num_resultsNo每个引擎返回几条,默认 5;Exa 最多 100(超过 10 条每多 10 条加收积分),其它引擎最多 10
exclude_domainsNo
include_domainsNo

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?

Beyond readOnlyHint/openWorldHint it discloses cost behavior in detail: 1–4 credits per call depending on engine and depth tier, Exa surcharges above 10 results, no charge on failure, and that the result tail reports credits spent and remaining balance. These are operational facts an agent cannot infer from annotations or schema.

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, then mode selection, then per-engine guidance, then cost — a logical order. The engine-by-engine enumeration is long but each entry carries selection signal, so it earns its space; only minor tightening is possible.

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?

For a 10-parameter, no-output-schema search tool, the description covers return content, engine semantics, and pricing side effects, and points to list_engines for exact tiers. An agent can call it correctly and predict the cost/result envelope without further lookup.

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 70%, and the description closes key gaps: engine/engines mutual exclusivity with anysearch as default, high cost tiers for depth=advanced/deep, and the Exa-specific 100-result cap with per-10 surcharge. It says little about language, time_range, merge, or include/exclude_domains, which are left to 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?

The description opens with a specific verb and resource (联网搜索) plus the concrete return shape (标题、链接、摘要), and immediately distinguishes the single-engine vs multi-engine modes and the default engine. An agent knows exactly what it gets back and how the call differs from list_engines/get_balance.

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?

It explicitly routes the agent: '想用某家就指定 engine;不指定则用默认引擎(anysearch);想对比就传 engines', then gives a per-engine selection rationale (exa for English/semantic, serpapi/serper for Google results, bocha/baidu for domestic Chinese, etc.). This is a genuine when-to-use-which guide, not an implied one.

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.

Resources