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

With no annotations, the description carries the full disclosure burden and does well: it states the price ($0.002 USDC/call), the payment protocol (x402, eip155:8453), the authoritative source (ECB), the calculation method (direct, cross via EUR, or peg-derived), and that values are deterministic rather than estimated. It stops short of covering rate limits, retry/failure behavior, or whether a value is ever absent for non-trading days.

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 plus a bracketed pricing prefix, front-loaded with the resource and then the provenance details. Dense but every clause (source, method, attribution, no-estimate) adds decision-relevant information; the closing 'Deterministic, sourced, no estimate' slightly restates what precedes it.

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 no-parameter tool with no output schema and no annotations, the description does well to preview the returned fields (rate date, method, source attribution). However, it never describes value format (decimal precision, quoting convention per unit), which matters for a rate tool whose output is otherwise undocumented.

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?

There are zero parameters, so the schema cannot be enriched and the baseline of 4 applies. The description implicitly confirms the call takes no arguments by fixing both currencies and the single latest fixing in the text.

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 the exact resource and scope: 'Official KRW/GBP reference rate' from the 'latest European Central Bank fixing', including the peg fallback. Because each sibling tool is pair-specific, the fixed currency pair in the name plus the stated source is enough to tell this apart from fx_gbp_krw, fx_latest, or fx_convert.

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: fetch the reference rate for KRW in GBP. The description never says when to choose this over fx_convert (for actual conversion), fx_latest (multi-pair snapshot), or fx_timeseries (history), nor does it state any exclusions such as unsupported dates or non-ECB currencies.

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