Screen untrusted content (web pages, emails, tool output) for prompt-injection/manipulation before your agent trusts it. Returns a risk score + reasons; a screening signal, not a guarantee. (security; $0.005/call in USDC via x402, 30 free/day).
| Name | Required | Description | Default |
|---|---|---|---|
| deep | No | Use the ML classifier too (default true). | |
| text | Yes | Untrusted content to screen. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It reveals the return format (risk score + reasons), the limitation (not a guarantee), and even pricing (USDC via x402, 30 free/day). This is valuable context beyond the schema, though it doesn't detail the risk score scale or deep parameter behavior, which are adequately covered by the schema.
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 exactly two sentences, front-loaded with the core purpose, followed by output/limitation and then pricing. Every sentence adds distinct, useful information with no redundancy. This is a model of concise, well-structured tool documentation.
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?
Given the tool's simplicity (two params, one required, no output schema), the description is remarkably complete. It covers the use case, the output, the limitation, and the cost model. Combined with the schema's full parameter descriptions, an agent has enough information to decide when and how to call this tool correctly.
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%, so baseline is 3. The description does not add new meaning to parameters; it only aligns with the schema's 'text' field as untrusted content. Since the schema already fully describes both parameters, the description's lack of parameter detail is acceptable.
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 clearly states the tool's function: 'Screen untrusted content for prompt-injection/manipulation before your agent trusts it.' It specifies the resource (untrusted content) and the action (screening), and differentiates from sibling URL/reputation tools by focusing on content-level security analysis.
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 clear usage context: use this when handling untrusted text content (web pages, emails, tool output) before trusting it. It also adds a caveat ('a screening signal, not a guarantee') that helps set expectations. Though it doesn't explicitly mention alternatives, the distinct purpose makes it evident when to choose this tool over siblings.
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.
Most tools have clearly distinct purposes, but there are overlapping pairs: unfurl_url/get_oembed/find_favicon all provide URL metadata, and render_page/screenshot_page both render a page (render_page can also screenshot). Descriptions help disambiguate, so only minor confusion is likely.
Tool names mix verb_noun patterns (check_domain, extract_content) with noun_verb patterns (dns_lookup, ssl_lookup, whois_lookup). Additionally, guard_inspect and guard_tx deviate from the typical verb-first style. The naming is readable but not consistent.
With 19 tools, the server is at the heavier end of the scale. While it covers a broad web-intel toolkit, several tools feel out of place for a 'fetcher' (e.g., generate_qr, guard_tx, guard_inspect), making the set feel bloated and unfocused.
The core web-fetching and analysis surface is well covered: DNS, WHOIS, SSL, headers, content extraction, rendering, screenshots, feeds, embeds, redirects, and robots. Missing is a simple raw HTML fetcher, but extract_content and render_page likely cover most needs. The addition of security and utility tools doesn't fill obvious gaps.
