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

With no annotations, the description carries the full burden and does reasonably well: it discloses the paid x402 micropayment ($0.002 USDC on eip155:8453), the authoritative ECB source, the peg fallback, the returned metadata (rate date, method, attribution), and the determinism/no-estimate guarantee. Gaps remain around non-publication days (ECB/TARGET holidays), caching/staleness of the fixing, and what happens on payment failure or for unsupported pairs.

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 payment/transport tag then the core definition, and every clause adds information (source, fallback, returned metadata, determinism). Slightly dense with comma-separated metadata lists, but no filler or repetition.

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?

With no annotations and no output schema, the description must stand in for the return contract, and it partially does by enumerating rate date, method, and source attribution. It omits the most consequential detail for a consumer — the direction convention (XOF per CHF vs CHF per XOF) and the numeric field name — which an agent needs to interpret the result correctly.

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, which is the baseline-4 case; the description correctly implies nothing needs to be supplied (the pair is baked into the tool name). It does not, however, clarify the quoting convention, which for a parameterless FX tool is the only semantic an agent could get wrong.

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?

States a concrete resource (the official XOF/CHF reference rate) and its provenance (European Central Bank fixing, or the official peg), so an agent knows exactly which pair and which source this returns. The pair-specific name and ECB framing separate it from the hundreds of other fx_* siblings without needing the schema. It stops short of naming the aggregator siblings (fx_convert, fx_latest, fx_timeseries) that could also surface this rate.

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: use this when you need an authoritative XOF/CHF rate rather than an estimate, and it explains the peg fallback. However, there is no explicit routing guidance against fx_convert (which could derive the same cross) or fx_latest/fx_timeseries, and no stated precondition beyond paying the per-call fee. An agent must infer when this beats the generic conversion tool.

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