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

Beyond the readOnly/idempotent annotations, it discloses pricing ($0.01 per call), the exact paid endpoint (GET /token/risk), that the call must be made with an x402 or MPP client, and that bad input is refused before any charge. These are non-obvious interaction traits the 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 purpose and scope are front-loaded in the first sentence, with the sibling pointer at the end. It is dense but every clause carries weight; the x402 mechanics occupy a long stretch that could be tightened slightly.

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 appropriately explains that the response schema and an example are returned by the paid request, so the agent knows it must make a second call to obtain data. For a tool with an unusual two-step paid flow, this is complete.

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 description coverage is 100%, so the schema already documents chain, address, and request_key semantics. The description adds no parameter-level detail (e.g., which chains are supported or how request_key behaves) beyond what the schema provides, so the baseline of 3 applies.

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+resource (rule-based risk label on an ERC-20 token) and enumerates exactly what is checked: OFAC SDN matches on token/owner/proxy admin, upgradeable proxy, and owner mint/pause/blacklist functions. It explicitly distinguishes itself from the sibling wallet_risk (token contract vs. wallet).

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?

It states the when ('before you accept or route it') and the explicit alternative ('For a wallet (not a token contract) use wallet_risk'), which is exactly the sibling an agent would confuse it with. Nothing is left to inference.

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