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 substantial work: it discloses cost ($0.002 USDC/call), the payment protocol and chain (x402, eip155:8453), the data provenance (ECB fixing or official peg), and the determinism guarantee ('Deterministic, sourced, no estimate'). Returned fields (rate date, derivation method, source attribution) are also previewed. It stops short of failure modes, e.g. what happens on weekends/holidays when no fixing is published, or what a failed payment returns.

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 sentence, front-loaded with the price/payment banner an agent needs before committing to a paid call, followed by the data source and the returned fields. Slight redundancy between 'Official ... reference rate', 'source attribution', and 'sourced', but there is no filler.

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?

No output schema exists, so the description must convey return contents, which it does (rate, rate date, derivation method, attribution). For a zero-parameter, single-pair rate lookup with a disclosed price, this is nearly sufficient; only the no-fixing-available case and call failure behavior are unspecified.

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 the baseline is 4. However, the description adds no parameter guidance at all — the pair is baked into the tool name rather than selectable, and there is no discussion of date selection or direction (XOF→CAD vs CAD→XOF), which an agent calling a rate tool would plausibly wonder about.

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 specific resource and verb-substitute: 'Official XOF/CAD reference rate: latest European Central Bank fixing', naming the currency pair, the source, and the peg fallback. It is clearly distinguishable from the hundreds of fx_* siblings by the explicit pair. It does not differentiate from aggregate siblings like fx_convert, fx_latest, or fx_timeseries, which is the only clarity gap.

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?

The phrase 'latest ECB fixing' implies a single-pair spot lookup versus a conversion or time-series call, but no alternative is named and there are no exclusions. An agent must infer that fx_convert should be used for arithmetic and fx_timeseries for history, which is left unstated.

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