Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, openWorld, idempotent and non-destructive, but the description adds the commercial and failure semantics that matter: 0.003 USDC per call via x402, no account/API key, invalid input refused before payment, failed runs never charged, and PaymentRequired returned without payment. That is exactly the context an agent needs before invoking a paid endpoint.

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 front-loaded with the core check and then adds payment/error behavior and a sample pointer, all of which earn their place. It is dense and slightly run-on, and the duplicated raw HTTP URL is arguably unnecessary for an MCP caller, which keeps it from a 5.

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?

For a two-parameter tool with no output schema, the description covers the return fields thoroughly, explains pricing and payment failure behavior, and points to get_example for a free sample. An agent has enough to decide, call, and interpret the result.

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 coverage is 100%, so the baseline is 3. The description still adds semantic context by listing the keyword among checked outputs and saying the keyword 'must appear on the page,' and by noting that the url may be a URL or domain. That modest extra meaning lifts it above baseline.

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 states a specific check ('Is it up, right now, from the internet') and enumerates exactly what is reported: HTTP status, final URL, DNS/connect/TLS/TTFB timings, HTTP version, size, content type, server, cert days left, and keyword match. That is far more precise than siblings like site_audit or url_safety_check, and an agent can tell which question this tool answers.

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?

It gives a clear when-to-use context: 'For monitors, deploy checks and agents that must not act on a dead site.' That condition selects it over observational siblings such as domain_intel or link_preview. It does not name an explicit alternative or exclusion, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.