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

Annotations already declare readOnly/idempotent/openWorld, and the description adds genuinely new behavioral facts: a 30-second API/MCP shared cache with checkedAt and cached fields to inspect, bounded retry attempts, no API key required, and the interpretive caveat that a blocked or inconclusive result is not proof of a global outage. The caching and retry disclosure is exactly the context annotations cannot carry.

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 usage condition, then output contents, then caveat, then operational notes. No sentence is filler, and the alternative-tool pointer is placed at the end where it does the least harm to the trigger statement.

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?

An output schema exists, so the brief output enumeration is sufficient rather than redundant, and the description supplies the operational details an agent needs: caching window, retry behavior, and how to interpret inconclusive results. Nothing material is missing for a one-parameter read-only probe.

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?

With a single required parameter at 100% schema coverage, the schema already fully documents the url field including the exclusions (no credentials, private addresses, nonstandard ports). The description confirms the target is a public website but adds no format or syntax detail beyond the schema, so the baseline of 3 applies.

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 ('fresh server-side availability observation' of a website) and enumerates concrete outputs: HTTP status, DNS answers, redirect chain, HTTPS connection evidence, timestamps. This clearly separates it from sibling tools like get_service_status that serve curated data.

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?

Explicitly names the trigger ('when a public website will not load') and the alternative for curated data ('use get_service_status'), which is strong routing guidance. It does not mention the sibling check_dns as the cheaper option for a DNS-only question, even though DNS answers are one of its outputs, so one alternative is left unaddressed.

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