units.fx_convert

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

Annotations already declare readOnly/idempotent/closed-world, and the description adds genuinely non-obvious behavior: the half-even default rounding mode, the full alternate-rounding list, the per-currency decimal table (JPY/KRW=0, USD=2, KWD=3, others=2), and that rate is a positive from→to directional value with no lookup. It stops short of stating error conditions (e.g. non-positive rate, unknown currency handling), so not 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?

Four tight sentences with the computation and return shape front-loaded, followed by precision rules, rounding options, and the rate caveat. Dense but every sentence carries information; nothing is filler.

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 pure-function tool with an output schema and safety annotations, this covers the semantics an agent needs: what is computed, how it is rounded, what precision applies, and that no rate lookup happens. Only the absence of sibling routing and error-case notes keeps it from full marks.

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 0% and there are no enums, so the description carries the full burden, and it largely does: rounding's six legal values plus default, rate's direction and positivity, to_ccy's role in determining precision, and amount's string output form. The one gap is the expected string format/precision of the input amount.

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 first sentence gives a specific verb-chain and output: multiply amount by rate, round to to_ccy's minor units, return an amount string plus currency. It is unmistakably a currency conversion, but it never distinguishes itself from sibling units.convert or units.fx_triangulate, which an agent could easily confuse it with.

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 closing clause 'rate 는 ... 환율을 조회하지는 않는다' usefully tells the agent it must supply its own rate rather than expecting a lookup, which implies usage context. However, there is no explicit statement of when to pick this over units.convert or units.fx_triangulate, so routing is left to inference.

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