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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: a per-caller daily quota on the free tier, and the requirement that payment credentials (X-Payment / X-Payment-Tx / Authorization: Bearer fg_…) go in MCP request headers rather than tool parameters — an agent would otherwise pass them as arguments and fail. It does not explain quota-exhaustion behavior or error responses, which keeps it from a 5.

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 verdict/output information is front-loaded, which is good, but the same facts are stated three times across the opening sentence, the ｜ clause, and the [zh]/[en] block (free tier, args list, purpose). The mixed Chinese/English duplication costs space without adding information, and the payment-header note — arguably the most actionable line — is buried at the end.

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 2-parameter read-only tool with no output schema, the description covers what an agent needs: what it returns (verdict, hit count, category codes, contract flag), the cost model, and how to authenticate. The main missing piece is routing versus the sibling address_report and address-risk tools, which matters given the crowded address-risk namespace.

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 must carry the load, and it does: address is declared required and chain is declared optional with the concrete accepted values eth/base/bsc, which are not present as an enum anywhere in the schema. The remaining gap is address format (raw hex vs checksummed vs ENS-like) and chain default behavior, so it is not fully compensating.

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 gives a specific verb+resource: screen an address for scam involvement and return an ok/caution/danger verdict plus hit category codes. It also discloses the concrete output fields (hit count, category codes, contract flag), which is more than a name restatement. It stops short of a 5 because it never names or distinguishes the sibling address-safety.address_report or address-risk.* tools, so the agent must infer that this is the lightweight '初筛' tier rather than the full report.

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 word '初筛' (preliminary screen) and the 'free' framing suggest a cheap first pass, and the free daily quota hints at cost-sensitive use. There is no explicit when-to-use/when-not statement and no pointer to address_report or address-risk.quick/risk as the alternative for deeper analysis.

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