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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful context beyond that: the upstream source is Frankfurter with ECB reference rates updated daily, and the service is free with no API key required, which tells the agent there is no auth step or credential prerequisite. It does not describe failure behavior for invalid currency codes.

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 facts (what it does, source, freshness, no key needed, empty-target behavior) are front-loaded and easy to scan. The cost is that every sentence is duplicated verbatim in Chinese, doubling length, though that duplication is clearly deliberate localization rather than padding.

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 three-optional-parameter read-only lookup with full schema coverage and read-only annotations, the description supplies the missing operational context: source, update cadence, and no-auth access. With no output schema present, it could have stated what the response contains (rate value vs. converted amount), which is the one remaining gap.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: base and target accept either ISO currency codes or Chinese currency names, and an empty target returns a basket of common currencies. That name-vs-code flexibility is non-obvious and materially improves correct invocation. It does not clarify the conversion output shape when amount is omitted.

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 concrete resource and action: live currency exchange rates plus amount conversion, and identifies the data source (Frankfurter / ECB reference rates). An agent can tell immediately this is a read-only FX lookup tool, clearly distinct from the weather, IP, and mycel siblings. It stops short of a crisp single-verb framing because the opening is a noun phrase rather than an imperative.

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?

The description implies usage through the 'leave target empty for a basket of common currencies' instruction, which is really parameter behavior rather than tool selection guidance. There are no sibling tools that overlap in function, so alternatives are not needed, but there is also no statement of when-not-to-use (e.g., historical rates, crypto, or non-ECB currencies are out of scope).

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