Check a URL before an agent clicks or cites it: status, redirects, dead/parked, phishing flags.
Scored across 1 tool
With only one tool exposed, there is no possibility of tool selection error — the agent can only call `preflight`. The description clearly states what the tool does and its boundaries (no page content extraction).
There is only one name, so there is no inconsistency to penalize. However, `preflight` does not follow the verb_noun convention seen in larger servers, leaving no stated pattern for future tools.
The server's scope is narrow and the single tool is rich (status, redirects, parked detection, content-type, llms.txt, abuse flags), which fits the purpose. Still, a one-tool surface is thin — sub-checks like reputation or robots.txt would naturally be separate operations.
For the preflight/URL-safety domain, coverage is broad: availability, redirect chain, dead/parked detection, metadata, llms.txt presence, and phishing signals. Minor gaps exist (no batch checking, no robots.txt/TLS detail), but agents can work around them.
Check a URL before you click, cite, or fetch it. Returns HTTP status, redirect chain and final URL, dead/parked-domain detection, content-type and size, whether /llms.txt exists, and phishing/abuse flags from public feeds plus heuristics. One call, no page content extraction. Free: 200 checks/day.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute http(s) URL or bare domain |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: the exact result fields returned, the explicit non-behavior ('no page content extraction'), and a concrete quota ('Free: 200 checks/day'). That quota and the enumerated output surface are exactly the kind of operational detail an agent needs and cannot infer from 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?
Front-loaded with the purpose, then a compact enumeration of returned signals, then the two key constraints (no extraction, daily quota). Three sentences, no filler, and the most decision-relevant information (what you get back) sits early.
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 present, the description carries the burden of describing return values and does so thoroughly across status, redirects, domain health, content metadata, llms.txt, and abuse flags. Combined with the read-only annotation and the stated quota, an agent has everything needed to call this correctly and interpret results.
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?
There is a single parameter, and the schema description already covers it fully ('Absolute http(s) URL or bare domain'), so schema coverage is 100% and the baseline is 3. The description adds no further syntax, normalization, or validation detail about the url argument, so it neither compensates nor detracts.
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 ('Check a URL') and immediately enumerates the concrete outputs: HTTP status, redirect chain, dead/parked detection, content-type/size, /llms.txt presence, and phishing/abuse flags. The phrase 'no page content extraction' draws a sharp boundary that distinguishes it from a generic fetch tool, so an agent knows exactly what class of operation this is.
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 opening clause 'before you click, cite, or fetch it' gives clear situational triggers, and 'no page content extraction' implicitly routes content-retrieval needs elsewhere. It does not name an alternative tool explicitly (there are no siblings), and it omits any exclusions such as authenticated or non-http URLs, so it falls short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
preflightURL reality check for agents: status, content hash, classification, wayback fallback.
Flags phantom-squatted/typosquatted domains and known-malicious URLs before an agent follows them.
AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.
URL intelligence for AI agents and developers. 16 tools, 25 signal weights, 20 free checks.
Add one secure layer between your agents and this server.