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

The description says 'PAID ($0.001 USDC via x402)' and the schema describes an EIP-3009 transferWithAuthorization payment, which is a payment side effect, while annotations declare readOnlyHint=true. This is a direct contradiction: a paid call is not read-only in the usual MCP sense, and the description even notes that a failed call is NOT charged, implying a successful call can charge. Flagged as annotation contradiction.

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?

Four short sentences front-load the cost first, then the resource and use case, then the payment and failure behavior. Every sentence carries operational information with no 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?

The description covers the resource, units, use case, payment flow, and failure semantics, and an output schema exists so return values do not need to be described in prose. It is only held back because the contradictory readOnlyHint means an agent relying on metadata rather than the description may be misled about side effects.

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 for the single payment parameter is 100%, and the schema already explains omitting it on the first call, sending it on the second, and forwarding it as the PAYMENT-SIGNATURE header. The description adds the automatic fiatdock-mcp payment behavior, but that is operational context rather than new parameter semantics, so the baseline 3 is appropriate.

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 identifies the resource: the current Base gas price in wei and gwei, and gives the intended use case of sampling before submitting a transaction. It does not explicitly state a verb like 'get' or distinguish itself from sibling price tools such as token_price, so it stops short of full sibling differentiation.

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 provides a clear when-to-use signal: a gas-aware agent samples this before submitting a tx. It also explains the payment flow, including that the first call omits payment and returns a 402 challenge, but it does not mention alternatives or when-not-to-use conditions.

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