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

With no annotations, the description carries the full burden and does well: it discloses cost ($0.002 USDC/call), the payment protocol and chain (x402, eip155:8453), the data provenance (ECB fixing, with an official-peg fallback when GBP is pegged), the returned metadata, and that values are deterministic rather than estimated. Left unstated are refresh cadence/staleness limits and what happens on payment failure or unavailable fixings.

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 of substance plus a bracketed cost/payment prefix. The cost tag is front-loaded and valuable for agent planning, and the core purpose follows immediately; nothing is redundant, though the bracketed preamble is dense with scheme identifiers that could be split or deferred.

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 parameters and no output schema, the description must describe the return payload itself, and it does (rate, rate date, derivation method, source attribution). The remaining gap is quote direction — 'PLN/GBP' does not resolve whether the value is PLN per GBP or the inverse — plus no freshness window.

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; the description still usefully pins down that the call returns the *latest* fixing rather than a caller-specified date, which is the only semantic an agent could otherwise 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?

Names a specific resource and scope: 'Official PLN/GBP reference rate: latest European Central Bank fixing.' The currency pair in the tool name is restated with the authoritative source, so an agent can distinguish it from neighbouring fx_* siblings without opening anything else.

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 by the pair itself; there is no explicit statement of when to prefer this over fx_convert (for amounts), fx_latest (for all pairs) or fx_timeseries (for history). The one genuinely useful usage fact is the paid/402 requirement, which tells the agent a payment flow is needed.

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