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

Annotations already cover read-only/idempotent/non-destructive, so the description's real contribution is the paid-call model and the credential mechanics: payment goes in MCP request headers (X-Payment / X-Payment-Tx / Bearer fg_…), explicitly not in params. That is a genuine invocation-critical detail not present in annotations, and the promised data-gap disclosure sets return expectations.

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 purpose is front-loaded, but the body duplicates itself across English and Chinese sections, restating the price and argument list twice. Worse, the two price statements conflict ($0.005 in the headline vs $0.07 USDC per call), which is noise an agent must reconcile rather than useful information.

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 does a fair job of describing what comes back (score, penalty reasons, on-chain facts, data gaps) and how payment is supplied. It remains incomplete on the one low-coverage parameter (`chain`: default behavior, accepted values, address-format expectations) for a tool whose input schema documents nothing.

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 0%, so the description carries the burden, and it only enumerates the argument names ("入参：address、chain") without explaining what `chain` does when omitted (it defaults to null) or how address format is validated on each network. It does add some value by scoping supported networks to Base and Ethereum, which partially informs the `chain` parameter.

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 opening line gives a concrete use-case framing ("is this wallet address risky") plus the exact deliverable: a 0-100 risk score, per-signal penalty reasons, all on-chain facts, and data-gap notes. The word "full" hints at a lighter sibling, but no sibling is named, so an agent must infer the distinction from the name `address-risk.quick` alone.

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?

Usage is implied rather than stated: the description signals this is the comprehensive variant and discloses a per-call price, which lets an agent reason about cost/benefit versus a cheaper option. However, it never says when to prefer this over a quick/screening tool, nor does it state prerequisites or limits that would exclude it.

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