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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add context, and it does: it discloses what the free verdict includes versus what the paid tiers add (OFAC SDN, scam lists, deployer, cross-chain, age, exposure). It also states that failed calls aren't charged and that credits auto-refund while x402 settles only on success, which is meaningful operational behavior an agent needs before spending money.

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 action and verdict vocabulary are front-loaded in the first sentence, with payment details relegated to the back. However, the tier prices are repeated verbatim in both the description body and the hub boilerplate, and the x402/credits mechanics consume a large share of the text relative to the core check.

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?

There is no output schema, so the description must carry return-value information, and it does by enumerating the free-tier fields and the paid evidence categories. What remains thin is the shape of the verdict itself and how confidence should be interpreted, but an agent has enough to call the tool and read 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?

With 100% schema coverage the baseline is 3, but the description adds real meaning by explaining that intent changes which signals matter (e.g. paying a token contract versus approving an EOA) and that a base58 address implies Solana. The prose largely restates the schema's tier pricing and chain list rather than adding new semantics, which keeps it from a 5.

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 verb and resource: 'before paying, approving or interacting with an EVM (Base, Ethereum, Polygon, Arbitrum One) or Solana address, get ok / caution / block.' That tells an agent exactly what comes back for a given address. It does not explicitly distinguish itself from near-siblings like screen_address or check_token, so it falls short of the sibling-differentiation bar for a 5.

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 'before paying, approving or interacting' framing gives a clear when-to-use trigger tied to the tool's intent parameter. The free-versus-paid guidance is explicit, including that omitting tier with no credits key yields the free tier. There is no explicit when-not-to-use or naming of an alternative sibling for address screening.

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