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

No annotations are provided, so the description carries the full burden. It usefully signals this is a '試算' (estimation/simulation) rather than a real transaction and names the rate source, but it omits the return format, whether rounding or fees apply, and any rate-freshness caveats.

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 front-loaded sentence with the tool's core mapping (rate source, direction, cash/spot) packed in efficiently and no filler. Slightly dense for a 0%-coverage schema, but no wasted words.

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 4-parameter, 0%-coverage, no-annotation, no-output-schema tool, the description is only partially sufficient: it explains direction and type but says nothing about cur/amount handling or what the result contains. Minimum viable but with clear gaps.

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 description coverage is 0%, so the description must compensate. It does add real meaning for two enums, defining buy as TWD→foreign and sell as foreign→TWD, and cash vs. spot, but leaves 'cur' and 'amount' completely unexplained.

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?

Names a specific verb+resource (convert/currency) and sharpens it with the rate source (Bank of Taiwan posted rates) and the two directions of exchange. An agent knows exactly what it computes, though it never distinguishes itself from the sibling exchange_rates tool.

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 its purpose ('試算換匯' – simulate an exchange) and clarifies the buy/sell and cash/spot cases, but gives no explicit when-to-use, when-not-to-use, or reference to the sibling exchange_rates tool for raw rate lookup. Usage is inferable rather than stated.

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