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

With no annotations supplied, the description carries the full burden and does well: it discloses the price and payment protocol up front ($0.002 USDC/call, x402, eip155:8453) and describes data behavior beyond the surface — ECB fixing source, peg fallback, rate date, derivation method, and source attribution. It stops short of explaining holiday/weekend staleness of the 'latest' fixing or the failure/payment-error path, which matters for a paid call.

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?

Two sentences, front-loaded with the cost/payment tag an agent must see before calling, followed by the substantive data provenance. Every clause (source, peg fallback, date, method, attribution, determinism) adds distinct information with no repetition of the 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?

For a 0-param tool with no output schema and no annotations, the description covers source, derivation method, returned metadata, cost, and payment rail — enough to call it correctly. The gap is the absence of any indication of the response's field shape or what happens on holidays when no new ECB fixing exists, which the missing output schema would otherwise have 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?

The tool takes zero parameters, so there is no parameter semantics to add beyond the schema; the baseline for a 0-param tool is 4. The description correctly implies the currency pair is fixed by the tool identity rather than supplied at call time.

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 specific resource (official USD/AUD reference rate) and pins down its provenance (ECB fixing, or the official peg when pegged), so an agent knows exactly which of the hundreds of fx_* pair tools this is. It does not, however, distinguish itself from directional or aggregate siblings like fx_aud_usd, fx_latest, or fx_convert, leaving the pair-selection logic to the name alone.

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' hints that this should be preferred when an authoritative reference rate is needed rather than a derived estimate, but there is no explicit when-to-use or when-not-to-use statement. No alternative tool (fx_convert for arithmetic, fx_timeseries for history, fx_latest for a generic lookup) is named or excluded.

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