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

With no annotations, the description carries the burden well: it discloses the paid access model ($0.002 USDC/call via x402 on eip155:8453), the deterministic/no-estimate guarantee, and the returned provenance fields (rate date, derivation method, source attribution). Missing are freshness semantics (weekend/holiday behaviour of the ECB fixing) and failure behaviour when no fixing exists, which matter for a rate-consuming agent.

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 dense sentence that front-loads the most decision-relevant fact first (paid, exact price, payment rail), then the data semantics. Every clause earns its place; the only minor cost is that the pricing tag occupies the lead position ahead of what the tool actually returns.

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, the description covers what an agent needs: what rate, from which source, with which derivation method and date, plus cost. It stops short of describing the response container or error payloads, but with no output schema and a trivially simple contract, that gap is small.

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 schema has zero parameters, so there is nothing to disambiguate; the baseline for a parameterless tool applies. The description correctly implies the pair is fixed by the tool identity rather than passed in, which prevents an agent from hunting for currency arguments.

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 the exact resource (ILS/PLN reference rate), the authoritative source (European Central Bank fixing), and the fallback semantics (peg-derived rate when PLN is pegged). An agent can distinguish this from the many fx_* siblings (e.g. fx_pln_ils, fx_ils_eur) purely from the pair and the 'official ECB fixing' qualifier.

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' signals this is the tool for authoritative reference rates rather than market/estimated quotes, and the ECB attribution signals official-fixing use cases. However, it never names an alternative (fx_convert for conversion, fx_pln_ils for the inverse direction, fx_latest for multi-pair retrieval) or states when NOT to use it, so the agent must infer routing.

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