get_current_rates

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It establishes this as a read-only data fetch and lists the exact data points, which is the core of the behavior. However, it does not disclose the return format/keys, units (e.g., annualized percentages, exchange-rate basis), freshness of the data, or data source — details an agent would want before relying on the output.

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 sentence that front-loads the main claim ('Retorna taxas econômicas atuais do Brasil') and then packs the list of specific rates into the remainder. Every item in the enumeration earns its place by telling the agent exactly what data is available; there is zero 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 zero-parameter, no-output-schema fetch tool, the description is nearly sufficient: it names every data point returned and implies a read operation. The only gap is the absence of return-format/unit details, which would have helped since no output schema exists to carry that information. Overall selection and invocation (trivial with 0 params) are well supported.

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 has zero parameters, so per the rubric the baseline is 4 — there is nothing for the description to explain. Schema description coverage is trivially 100% on an empty schema, so no compensation is needed. The description's enumeration effectively tells the agent what payload to expect instead.

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 has a specific verb ('Retorna'), a clear resource (current Brazilian economic rates), and precisely enumerates the data points returned (Selic, CDI, IPCA, IGP-M, poupança, dólar, euro, salário mínimo). This enumeration inherently distinguishes it from the sibling calculators (calculate_net_salary, calculate_severance) and from get_inss_table / get_irpf_table, whose scopes are different tables.

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 context is only implied: an agent would use this when it needs current Brazilian rate values. There is no explicit when-to-use, when-not-to-use, or routing to an alternative (e.g., 'use calculate_inflation_adjustment when calculating over time rather than fetching current rates'). Given the large field of calculate_* siblings, an explicit contrast would materially help.

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