Crawl a website and extract emails, phone numbers, and social profiles.
Args:
website: The website URL to crawl (e.g. "example.com" or "https://example.com").
max_pages: Maximum number of pages to crawl (1-20).
| Name | Required | Description | Default |
|---|---|---|---|
| website | Yes | ||
| max_pages | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It does not state whether the tool is read-only, any potential impact on the target website, rate limits, or error handling. Crawling a website implies network access but lacks details such as whether it follows robots.txt, timeouts, or maximum crawl depth consequences. This is insufficient transparency for a tool that interacts with external sites.
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?
The description is appropriately brief and well-structured. The purpose is stated in the first sentence, followed by clear arg descriptions. Every sentence serves a purpose with no fluff or repetition.
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?
The tool is relatively simple with two parameters, but since there is no output schema, the description should clarify what the return value looks like. It mentions extracting emails, phone numbers, and social profiles but does not describe the format, whether it's a list or object, or how pages are aggregated. It also lacks any mention of errors or limits beyond max_pages. This is adequate but has clear gaps for a fully self-contained description.
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 fully compensates by explaining both parameters: website is the URL to crawl with examples, and max_pages is the maximum number of pages with a range (1-20). This adds meaningful context beyond the bare schema properties and helps the agent construct valid inputs.
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 opens with a specific action: 'Crawl a website and extract emails, phone numbers, and social profiles.' This clearly defines the tool's function and scope, distinguishing it from sibling tools like lookup_business or lookup_domain, which imply lookup operations rather than crawling.
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 provides no explicit guidance on when to use this tool versus the sibling tools. It does not mention alternative tools or describe scenarios where this tool is preferred. The only implicit guidance is that it's for crawling websites, but there is no exclusionary language or context for selection.
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 has a clearly distinct purpose: web contact extraction, company registration lookup, director search, domain intelligence, and financial statements. Even the two ONRC-based tools differ in query type (name/CUI vs director name), eliminating ambiguity.
Four of five tools follow the consistent 'lookup_' prefix with a clear noun (business, director, domain, financials). The fifth, 'extract_contacts', uses a verb-noun pattern but with a different verb. This is a minor deviation and still readable, but slightly breaks the uniform style.
With exactly 5 tools, the set is well-scoped for a lead-generation server. Each tool covers a distinct aspect of lead research without redundancy, making the count appropriate for the purpose.
The toolset covers the core leadgen workflow: find companies, identify directors, extract contacts, check domains, and review financials. Minor gaps exist (e.g., no social profile lookup or email verification), but the surface is sufficient for typical lead generation tasks.