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

With no annotations at all, the description carries the full burden and does meaningful work: it discloses a per-call price ($0.002 USDC), the payment protocol and chain (x402, eip155:8453), the underlying source (ECB), and that results are deterministic and not estimated. It omits failure/edge behavior such as what happens on non-publishing days or when a peg is absent, which keeps it from a 5.

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 with the cost/transport prefix, the core definition, and the qualifiers in a logical order. Every clause adds information and nothing is repeated from structured fields.

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?

There is no output schema, so the description must convey what comes back, and it does list the rate, rate date, method, and source attribution. What it leaves out is material for a pricing tool: the quote direction/convention (KRW per USD vs the inverse), numeric formatting, and behavior on days the ECB does not publish.

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 no parameter meaning to add; baseline is 4. The description instead spends its words on the returned fields (rate date, derivation method, source attribution), which is the right use of space.

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 verb+resource: the KRW/USD reference rate, and pins the exact provenance (latest ECB fixing, or the official peg when USD is pegged). This is enough to separate it from the many sibling pairs, but it never names the near-duplicate alternatives (fx_usd_krw, fx_convert, fx_latest), so the agent must infer direction and scope on its own.

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: the phrases 'official reference rate' and 'no estimate' signal this is the authoritative source rather than a computed conversion, which is a real differentiator against fx_convert. However, there is no explicit when-to-use, no when-not, and no named alternative for cases like conversion or historical series.

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