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

Annotations only declare readOnly/openWorld/non-idempotent/non-destructive; the description adds real behavior beyond that: the call is metered (0.001 RLUSD or 0.001 USDC), an unpaid call fails as isError with a PaymentRequired object rather than data, a fresh invoiceId is issued per challenge, and failed calls are free. That is exactly the kind of payment/auth and failure-mode disclosure an agent needs before invoking it.

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 single paragraph is dense but front-loads pricing (already in the title) ahead of the actual purpose, delaying the one-line question the tool answers. "Unpaid calls cost nothing" carries mild value but partly repeats the preceding isError sentence, and the payment mechanics dominate the space budget.

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?

For a paid query tool with no output schema, the description covers the unusual payment/failure path thoroughly but never describes what a successful observation result contains, and leaves open which of tx or invoiceId to pass given no required parameters. Adequate to invoke, incomplete about interpreting the answer.

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 only 33% — tx and invoiceId have no schema descriptions — and the description compensates only by implying either identifier answers the same question. It does not say whether the two are alternatives or may be combined, whether one is mandatory, or what identifier format to supply, despite zero required parameters. payment_signature's role is mostly restated from the schema rather than extended.

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 concrete resource and question: "What does our invoice/ledger observation show for this invoiceId or tx?" — a specific verb-and-resource pairing an agent can act on. It does not differentiate itself from nearby siblings like get_merchant_readings, batch_readings, or get_x402_activity, so it stops short of a 5.

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 gives a clear procedural path (call unpaid → receive PaymentRequired with fresh invoiceId → retry with signed payload via _meta["x402/payment"] or payment_signature), which is genuinely useful usage guidance. However, it never says when to prefer this tool over sibling lookup tools such as get_merchant_readings or batch_readings, nor any exclusions, so the alternative-selection guidance is absent.

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