Zovo FBAR Currency Converter

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it names the rate source (Treasury Reporting Rates of Exchange for Dec 31), the recorded-copy fallback with a source line carrying the recording date, per-account rounding up to the next whole dollar, and a 25-account ceiling. It also disclaims side effects (no filing, no obligation determination), which is exactly what an agent needs before calling.

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 trigger condition is front-loaded and every clause carries information (rate source, rounding, cap, limits). It is dense to the point of being a single long block, but no sentence 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 tool with four parameters, an output schema, and full annotation coverage, the description closes the remaining gaps: data provenance, rounding rule, capacity limit, and scope boundaries. Nothing an agent needs before invoking it is missing.

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 not in the schema: the 25-account cap is enforced in prose (the array has no maxItems), and the year-end rate semantics tie tax_year specifically to a December 31 rate from 2001 onward. Rounding and rate-source behavior further clarify what the numeric inputs will produce.

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 and resource (convert foreign account balances to USD at the Treasury year-end rate) plus the exact domain artifacts it serves (FBAR FinCEN 114, Form 8938) and the $10,000 threshold check. An agent can tell this apart from the sibling list_treasury_rates, which supplies rates rather than converting balances.

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?

Opens with an explicit trigger ("Use this when the user needs...") and closes with clear exclusions: it does not file forms, does not decide tax obligations, and does not convert at today's market rate. The only gap is that it never names list_treasury_rates as the alternative for looking up rates directly.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description goes beyond them by disclosing data provenance and fallback behavior ('live API tried first', 'recorded copy since 2001'), coverage limits since 2001, CSV output, and the direction of the rate values (foreign units per 1 USD) — all things an agent cannot get from annotations.

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?

It is front-loaded with the usage trigger and every clause carries information — no filler. The main cost is that it is a single dense sentence packing provenance, units, and the exclusion, which forces a careful read rather than skimmable structure.

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 read-only listing tool with a full output schema and complete parameter descriptions, this covers everything an agent needs: when to call it, what data source and fallback applies, the unit convention, the year range implicit in the schema, and which sibling to use instead. No meaningful gap remains.

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?

With 100% schema description coverage the baseline is 3, but the description adds real meaning beyond the schema: it clarifies that the choice is between the December 31 rate and the quarterly reports, which explains the relationship between currency and all_quarters, and it defines the unit semantics of the returned rate. It stops short of documenting the currency filter's code/country/substring flexibility, which the schema already handles.

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 specific verb and resource ('list ... the U.S. Treasury Reporting Rates of Exchange for a year') and pins down the exact scope: December 31 rate for one or all currencies, or quarterly reports. It is immediately distinguishable from the sibling convert_foreign_balances, which it explicitly names as the different 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?

It opens with an explicit trigger ('Use this when the user wants...') and closes with a when-not plus an alternative ('Does not give live market rates or convert balances (use convert_foreign_balances for that)'). Both the positive condition and the exclusion route the agent to the correct sibling without inference.

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