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

With no annotations at all, the description carries the full burden and does well: it discloses the paid model ("$0.002 USDC/call, x402, eip155:8453"), the provenance (ECB), the derivation method (direct, cross via EUR, or peg-derived), and asserts determinism with no estimation. What it omits is update cadence/latency, behavior on non-fixing days, and failure modes if the pair is unavailable.

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?

A single tight paragraph with no filler; the payment terms are bracketed and front-loaded so they can be skipped, and the core definition, source, method, and non-estimation guarantee follow in order of importance.

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 zero-arg, no-output-schema lookup, the description covers source, derivation path, date stamping, attribution, cost, and determinism — enough to call it correctly. The remaining gap is freshness cadence and peg-transition handling, which matter for interpreting the result rather than for invoking the tool.

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?

Zero-parameter tool, so the baseline of 4 applies; the description correctly clarifies that the currency pair is fixed by the tool name rather than supplied as an argument. The only added meaning is around what the returned rate carries (rate date, method, attribution).

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?

Names a concrete verb+resource pair ("Official SAR/KRW reference rate") and pins the exact source ("latest European Central Bank fixing"), including the peg fallback. An agent can distinguish it from fx_convert, fx_latest, fx_timeseries, and the hundreds of other fx_* pairs purely from the name-plus-description combination.

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?

Usage is only implied: "Deterministic, sourced, no estimate" signals this is the authoritative source rather than a model guess, which weakly routes an agent away from estimating or from fx_convert. But no sibling is named, there is no explicit when-not, and no statement of what to do for dates outside the latest fixing or for non-publication days.

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