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

Beyond readOnlyHint/destructiveHint, the description discloses cost, accepted payment rails and networks, the exact failure shape on unpaid calls (isError with a PaymentRequired object and fresh invoiceId), and the two retry channels (_meta["x402/payment"] or payment_signature). It also explains why the tool is non-idempotent — each call issues a fresh invoiceId — which reconciles the idempotentHint=false annotation with what looks like a pure read.

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?

Dense but nearly every clause carries load — price, rails, scope, error shape, retry path. The main flaw is ordering: it front-loads payment mechanics ahead of the one-line purpose, so an agent must read three clauses before learning what the tool looks up.

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?

There is no output schema, so the description is the only place the success return could be characterized — yet it describes only the error payload, leaving an agent unable to anticipate whether a hit returns a name, numeric code, minor units, or a not-found sentinel. Payment and failure behavior are otherwise thoroughly covered.

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 50%, and the undescribed parameter is the required one: the description never says whether q accepts an alpha-3 code ("USD"), a currency name, or a numeric code, nor whether matching is case-insensitive. The payment_signature alternative is only referenced by name, deferring to the schema that already documents it.

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?

"ISO 4217 currency code lookup from a bundled open table. No FX rates." names the exact resource, the lookup action, the data source, and explicitly excludes a neighboring concept (FX rates) that an agent might otherwise assume. This distinguishes it cleanly from siblings like country_code, iban_format, or get_price_index.

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 states the single question the tool answers and gives the full when-to-use gate (paid call, x402 required), plus the operational sequence for an unpaid first call. It stops short of naming alternatives such as country_code for jurisdiction lookups, so the routing guidance is clear but not exhaustive.

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