Search the web in real time using natural language to find technical docs, library versions, errors, and open-source solutions; returns titles, URLs, and summaries.
极速全网实时检索 (直连 Devin 官方网关)。用自然语言查最新技术文档、库版本特性、报错与开源方案，亚秒级返回结构化标题、网址与摘要。
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 搜索关键词或自然语言问题 | |
| detailed | No | 是否附带深度综合总结 | |
| num_results | No | 返回结果条数 (默认 5) |
Changes observed during successful MCP inspections.
v2.0.0Input schema / properties / detailed / descriptionPrevious value: -"是否返回深度 AI 综合总结与结论分析"New value: +"是否附带深度综合总结"Input schema / properties / max_resultsRemoved value: -{
- "description": "num_results 的兼容别名",
- "type": "integer"
-}Input schema / properties / num_results / descriptionPrevious value: -"期望返回的结果数量 (默认 5，建议 3-10)"New value: +"返回结果条数 (默认 5)"Input schema / properties / query / descriptionPrevious value: -"自然语言搜索查询 (例如: 'Next.js 15 features', 'Vue 3.5 reactive props')"New value: +"搜索关键词或自然语言问题"v1.0.6Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full behavioral burden; it does disclose the return shape (structured title, URL, summary) and a latency claim (亚秒级), and notes it connects directly to the Devin gateway. However it says nothing about authentication, rate limits, quota, or failure behavior, leaving meaningful gaps for a networked tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences: the first front-loads the core identity and speed claim, the second gives query domains and return format. No filler, though the speed claim ('极速'/'亚秒级') is somewhat redundant with itself.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 3-param search tool with no output schema and no annotations, the description covers purpose, applicable query types, return format, and latency. It omits auth/limit details, but nothing critical for correct invocation is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is already 100% (query, detailed, num_results are all documented in the schema), so baseline is 3. The description's '用自然语言' hint is effectively a restatement of the schema's own '搜索关键词或自然语言问题' text, adding no new parameter meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('极速全网实时检索') scoped to live whole-web search, and the query-domain sentence (technical docs, library versions, errors, OSS solutions) makes its remit unmistakable versus a page-fetch tool. It is inherently distinguishable from devin_web_fetch (single-page retrieval) and extract_devin_key.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear usage context by enumerating the query types it targets (最新技术文档、库版本特性、报错与开源方案), which tells the agent when to reach for it. It stops short of naming an explicit alternative or any when-not-to-use condition, so it is context without exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.