Crawl a website and extract its content as structured data.
Args: url: Website URL to crawl (e.g. 'https://example.com') max_pages: Max pages to crawl (default 5)
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| max_pages | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true and openWorldHint=true, so the safety profile is established. The description adds no additional behavioral context beyond the action itself—it doesn't mention potential slowness, site failure, or extent of crawling (e.g., same-domain only). No contradiction with annotations.
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 plus a brief args list—extremely concise with no filler. The main purpose is front-loaded in the first sentence.
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 doesn't specify what the structured data looks like or how crawling behaves. It's sufficient for a simple 2-parameter tool, but leaves ambiguity about return format and crawl scope.
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 0%, so the description carries the burden. It explicitly explains each parameter ('Website URL to crawl' and 'Max pages to crawl') and the default, which goes beyond the bare schema. However, the explanations are minimal and don't elaborate on edge cases or valid formats.
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?
The description uses a specific verb ('Crawl') and resource ('a website'), clearly distinguishing from sibling search/lookup tools. It also indicates the output type ('structured data'). This is a clear, non-tautological purpose statement.
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 implies when to use the tool (when you want to crawl a specific website) but provides no explicit guidance on when to prefer alternatives like google_search or wikipedia_lookup. No exclusions or edge cases are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct source: crawl_website for general sites, google_search for search results, and wikipedia_lookup for Wikipedia articles. There is no overlap or ambiguity in their purposes.
All tool names follow a consistent lowercase_underscore style, with clear action-oriented naming (crawl_website, google_search, wikipedia_lookup). The convention is uniform across the entire server.
With only 3 tools, the server is well-scoped for basic web retrieval tasks. Each tool fills a distinct role, and the count is within the ideal range for a focused MCP server.
The tool set covers core web scraping activities: crawling a site, searching the web, and retrieving a specific knowledge article. A minor gap is the lack of a standalone fetch tool for a single URL, but crawl_website with max_pages=1 can serve that purpose.