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

Goes beyond the annotations by confirming they hold in practice ('free, read-only, no network fetch') and by disclosing the verdict vocabulary (official | no_red_flags | caution | suspicious | dangerous). It also surfaces cost structure (free here, 0.005 USDC via x402 for the full check), which is genuine behavioral context. It does not explain latency, caching, or what happens on malformed input.

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 strongest claim (free, read-only, no network) and the action, with detail following. The parenthetical enumerations are dense but each earns its place by defining scope. The upsell clause is the longest single element and sits slightly awkwardly inside a tool description, but it does double duty as the alternative-route signal.

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, the description correctly compensates by enumerating the verdict values an agent will receive and listing the signal categories that drive them. Cost and the paid escalation path are covered. Missing only failure-mode behavior (what verdict or error an unparseable URL produces).

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% and the sole parameter already documents 'URL or bare domain'. The description repeats the same 'URL/domain' framing without adding syntax, normalization, or edge-case guidance, so it contributes nothing beyond the schema. Baseline 3 applies when the schema does the work.

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 names a specific verb and resource ('check a URL/domain for crypto phishing signs') and enumerates the exact signals checked (lookalike domains, punycode, free hosting, bait words). It also distinguishes itself from the richer sibling by framing itself as the free pre-connect pre-check, so it is clearly identifiable against full_report_info.

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?

States a concrete trigger context: 'before connecting a wallet or signing'. It also frames the alternative — the paid full check for domain age, DNS, redirects and page scanning — implicitly routing deeper-dive cases elsewhere. It never says when the tool is not appropriate (e.g., non-URL inputs or already-verified domains), which keeps it just 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.