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 paid access model ($0.002 USDC/call, x402, eip155:8453), the authoritative source, the method resolution logic (direct, cross via EUR, or peg-derived), and guarantees determinism with no estimation. It stops short of describing return format or how the rate date is chosen, which is the main remaining gap.

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?

One sentence that front-loads the cost and protocol tag before the substantive description, which is the right ordering for a paid tool. It is dense but every clause (source, peg branch, method, attribution) adds information; nothing is padded.

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-parameter, no-output-schema tool this is close to complete: the description enumerates the returned fields (rate, rate date, method, source attribution) so the missing output schema matters less. Not full marks only because freshness and the behavior when no fixing exists for a date are unaddressed.

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 are no semantics to disambiguate and the baseline applies. The description correctly avoids any parameter talk and instead spends its words on what the caller receives.

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 KRW/XOF reference rate) and a specific source (latest ECB fixing, or the official peg when XOF is pegged). The pair encoding in the tool name is confirmed and expanded rather than restated, so an agent can pick it over the hundreds of other fx_* siblings without opening a schema.

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 implied rather than stated: 'reference rate', 'deterministic, sourced, no estimate' signals the audit/compliance use case, and the peg-vs-fixing branch explains an output variation. But there is no explicit guidance on when to prefer this over fx_convert, fx_latest or fx_timeseries, nor any note about rate staleness that would tell an agent whether it is suitable for a given date.

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