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

Beyond the readOnly/idempotent annotations it discloses the commercial and mechanical behavior: $0.003 USDC per call on Base via x402, an unpaid call returns a PaymentRequired object, and the retry must carry params._meta['x402/payment']. It also bounds the result honestly by listing what was not checked, which is exactly the context annotations cannot convey.

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 controlling question is front-loaded and every clause is substantive — checked dimensions, output shape, price, payment flow, HTTP mirror. It is dense to the point of being a single run-on sentence, so scanning costs more than it should, but nothing is filler.

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 carries the return contract itself: a 0-100 score, one reason per flag, and an explicit not-checked list. Combined with payment mechanics and the HTTP endpoint, an agent has everything needed to invoke this correctly and interpret the response.

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 50%; only 'token' carries a description, and the description's re-listing of the eight chain names merely restates the enum rather than adding meaning (e.g. default chain, address format quirks). The only genuinely new parameter-level information is the _meta['x402/payment'] field needed on retry, which is useful but not schema-adjacent.

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: a deterministic risk screen of an ERC-20 token across eight named chains, computed from bytecode and eth_call only. It enumerates exactly what is inspected (proxy/admin, ownership, selector scan for mint/pause/blacklist/fee setters, supply concentration) and what is produced, which lets an agent separate it from metadata tools like token_info without opening a schema.

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 opening question 'Is this token centrally controllable?' establishes the decision this tool serves, and the 'no third-party risk API' clause plus the explicit 'no DEX sell simulation' caveat tells the agent what the screen will not answer. It stops short of naming alternatives (token_info, token_balances) or stating when-not-to-call, so it is clear context without exclusions.

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