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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds substantial context beyond them: paid access at 0.004 USDC on Base via x402, a 30-minute cache, ECB provenance, and the explicit guarantee that unsupported currencies are listed rather than guessed. It also clarifies wallet ownership ('your own wallet pays, never this server's'), which no annotation conveys.

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?

Front-loads the paid tag and the core capability, then layers provenance and the payment workflow efficiently. There is mild redundancy — '0.004 USDC on Base via x402' appears in both the tag and the body, and the payment re-call is repeated from the schema — but no sentence is wasted.

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 4-parameter, no-output-schema tool with a nested payment object, the description covers provenance, cost, caching, limitations, and the two-step payment dance thoroughly. It could say more about the shape of the returned rates, but the listing/never-guessed hint partially covers response expectations.

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 description coverage is 100%, so base, date, quotes, and payment_header are already documented, and 3 is the appropriate baseline. The description reinforces the payment_header workflow but adds no syntax or format detail the schema lacks.

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 opening sentence names a concrete resource (foreign-exchange reference rates), its scope (any base, up to 40 quotes, latest or historical back to 1999), and its provenance (ECB euro reference rates via Frankfurter). It also flags what it is not — 'end-of-day reference rates, not tradeable quotes' — which cleanly separates it from trading-oriented siblings like 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?

Gives explicit operational guidance: 'Call with no payment_header first to receive the payment requirements' and re-call with the signed payload plus the same business arguments. It stops short of naming the free fx_rates_preview sibling or stating when-not to use the paid path, so the alternative routing is left to inference.

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