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

Adds substantial behavior beyond the annotations: the dual-RPC receipt-agreement requirement, the finality gate, the fact that unsafe/failed/not-found txs return an assurance result rather than an error, and that RPC infrastructure failures refund the credit (cost model of 1 credit per call). The one loose end is destructiveHint=true, which the description never explains; the credit-consumption language reconciles readOnlyHint=false and idempotentHint=false (repeated calls recharge), but 'destructive' remains a stretch for a pure log-decoding operation.

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 sentences, purpose front-loaded, and every clause earns its place: purpose/finality gate, non-error outcome semantics, cost and refund policy. No restating of the title or name.

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?

An output schema exists, so return-shape detail is unnecessary, and the description covers preconditions, failure semantics, and billing. For a single-parameter tool it is nearly complete; the only meaningful omission is sibling differentiation against verify_usdc_payment, which an agent selecting between USDC tools would want.

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?

Only one parameter (txHash) and schema description coverage is 0%, so the schema's regex pattern carries the format while the description adds only chain context ('from a Base transaction', i.e. a Base tx hash). That is mild but real compensation for the coverage gap; it does not clarify whether the hash may be from another chain or what happens if the tx is not on Base.

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?

Specific verb (Decode) + precise resource (native Circle USDC Transfer logs) + chain (Base) and a scoping condition (only after dual-RPC receipt agreement and safe finality). An agent can distinguish this from siblings like get_transaction_status or verify_usdc_payment without opening any 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 description gives a real invocation precondition ('only after dual-RPC receipt agreement and safe finality') and states what happens for not-found/failed/not-yet-safe chains. It does not, however, name an alternative tool or an explicit when-not-to-use case among the siblings (verify_usdc_payment, get_transaction_status), so it stops short of full routing guidance.

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