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

The description clearly discloses the payment requirement (PAID $0.001 via x402), the 402 challenge behavior, the automatic payment by the fiatdock-mcp npm package, and the charging/non-charging behavior on error. It goes well beyond the annotations (readOnlyHint, openWorldHint, idempotentHint) and adds crucial context about payment and error handling. 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?

The description is well-structured and front-loads the most critical info (PAID, what it does, what it returns). The payment details are dense but necessary. It's a bit heavy on the payment mechanics, but every sentence serves a purpose. Slightly verbose could be trimmed, but it's efficient for a complex flow.

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 the complexity of the x402 payment flow, the description is remarkably complete. It covers the what, how to use, payment nuances, error handling, and charging behavior. The output schema exists, so return format is covered. There's nothing an agent needs to know to call this correctly that's missing.

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 100% and the description adds significant value. It clearly explains the payment parameter's role: it's a Base64 of an x402 v2 PaymentPayload, when to omit it (first call), what to do with the 402 response (howToPay.payloadTemplate), and that it's forwarded as a header, not body data. The address parameter is also clarified as requiring a 40-hex EVM address. This goes beyond the schema descriptions.

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 clearly states the tool reads the native ETH balance of any address on Base, in wei and ETH, and is distinct from USDC balance and other token tools. It names the exact resource (native ETH balance), the network (Base), and the return units, distinguishing it from siblings like usdc_balance and token_price.

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 description explicitly explains the two-call payment flow: first call gets a 402 challenge, second sends the payment payload and completes the purchase. It also clearly states when the tool is NOT appropriate or what happens on failure (invalid address returns 400 not charged, RPC failure returns 5xx not charged). It does not explicitly name alternatives, but given the sibling list includes usdc_balance, it implies this is for native ETH only. The payment mechanism guidance is thorough and prevents misuse.

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