Recursively traverses an entire site or subdirectory from an entry URL, returning each page's title, body text, and links for full-site scraping or documentation mirroring.
从入口 URL 递归爬取整站/子目录，返回每页标题+正文+链接。适合：整站抓取、文档站镜像。
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | 入口网址 | |
| deny | No | 跳过匹配该正则的链接 | |
| allow | No | 只爬匹配该正则的链接（如 ^/docs/） | |
| depth | No | 递归深度（默认 2） | |
| browser | No | 是否浏览器渲染（默认 false） | |
| max_pages | No | 最多抓取页数（默认 100） | |
| same_domain | No | 只爬同域名（默认 false） |
Changes observed during successful MCP inspections.
v2.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden: it does disclose the return shape and the recursive scope, which is useful. However, for a potentially heavy crawl it says nothing about rate limiting, timeouts, robots/politeness, or what happens when a page fails, and it never flags that same_domain defaults to false so the crawl may leave the domain.
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 sentences, zero waste, with the core action and scope front-loaded before the use-case hint. Every clause earns its place.
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?
With no output schema, the description usefully states the per-page return fields, and all seven parameters are covered by the schema. The remaining gap is behavioral: cost/duration and rate-limit expectations for a recursive crawler are unstated.
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 100% and the parameter descriptions are good (regex example '^/docs/', defaults for depth/browser/max_pages/same_domain), so the schema does the heavy lifting. The description adds nothing parameter-specific beyond the general notion of recursion, so the baseline 3 applies.
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 and resource: recursively crawl a whole site/subdirectory starting from an entry URL, and it also names the return shape (title + body + links per page). The word '递归' plus '整站/子目录' implicitly separates it from the single-page scrape sibling, but no sibling is named explicitly.
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?
'适合：整站抓取、文档站镜像' gives positive use cases, which is more than nothing. But it never says when NOT to use it, nor points to alternatives such as scrape for a single page or bulk_scrape for a known URL list, so the agent must infer the boundary from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.