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

Even with readOnlyHint/idempotentHint present, the description adds significant non-obvious behavior: the tool is paid at $0.02/call, requires a two-step x402 payment exchange, and only charges when a result is returned. No contradiction with annotations.

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?

Three dense sentences, with the cost and purpose front-loaded before the payment walkthrough. No filler or repetition of schema details.

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?

Given no output schema, the description names the expected result fields (grade, score, verdict prose, signals), and covers the only nontrivial call protocol (x402 payment). An agent has enough to invoke it correctly.

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?

The schema already documents all three parameters at 100% coverage, so the baseline is 3. The description goes beyond the schema by explaining the payment workflow: first call without x402_payment yields an accepts array, and the second call must include the base64 X-PAYMENT payload. This materially helps an agent use the optional parameter correctly.

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 the tool's specific job: produce HostDeFi A+–F verdicts for a chain+address, and lists the delivered fields (grade, score, verdict prose, liquidity/holders/authority signals). The resource and output are clear, though it never explicitly contrasts token_risk_deep or scan_token, so it doesn't fully differentiate among siblings.

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?

Provides explicit call sequencing: omit x402_payment on the first call to receive an accepts array, then pay and retry with the base64 X-PAYMENT payload. This is strong operational guidance, but it never states when to prefer this tool over a sibling like token_risk_deep, so it lacks a when-not/alternative statement.

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