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

With no annotations, the description carries the full burden and does a lot: it discloses paid access ($0.002 USDC via x402 on eip155:8453), the authoritative source, the possible derivation methods (direct, cross via EUR, peg-derived), and that values are deterministic and not estimated. Remaining gaps are around failure/freshness behavior — weekends and holidays when the ECB does not publish, and what happens if no fixing is available.

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?

The core meaning is stated first in one dense sentence, followed by a short provenance tag; the paid-cost prefix is meta but genuinely useful for an agent deciding whether to call. Nothing is redundant, though the bracketed payment preamble competes with the purpose statement for the opening position.

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 lookup tool, the description compensates well by enumerating the returned fields (rate, rate date, method, source attribution) and asserting determinism. It stops short of stating quote direction (1 GBP = X CZK), value precision, and staleness rules, which are the main things an agent must assume when no output schema exists.

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 is nothing for the description to disambiguate; baseline 4 applies. The empty schema matches the taken-as-given currency pair encoded in the tool name.

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 and source (GBP/CZK official European Central Bank fixing) and clarifies that pegs are handled, which is more than the name fx_gbp_czk conveys. It implicitly separates itself from amount-conversion siblings like fx_convert by framing the result as a 'reference rate' with no estimation, but it never names an alternative tool explicitly.

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?

Saying 'latest ECB fixing' implies the use case (need the official reference rate, not a computed cross), but there is no explicit when-to-use/when-not guidance and no routing to fx_convert for amount conversion, fx_timeseries for historical series, or fx_latest for multi-pair snapshots among the ~500 fx_* siblings.

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