Taxa de câmbio oficial de fechamento contra o real (compra e venda), para USD, EUR, GBP, JPY, CHF, CAD, AUD, DKK, NOK e SEK. Em fim de semana ou feriado devolve o último boletim publicado.
| Name | Required | Description | Default |
|---|---|---|---|
| pairs | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavior beyond the annotations: it returns both buy and sell rates, covers specific currencies, and on weekends/holidays returns the last published bulletin. This enriches the readOnly and idempotent hints already present in 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?
The description is two sentences, concise and front-loaded with the core purpose. It includes essential details without unnecessary 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?
The description covers the tool's purpose, currency scope, and fallback behavior, but leaves the input parameter format ambiguous. Without output schema or parameter guidance, an agent may struggle to invoke it correctly, though the tool's simplicity keeps it at a minimally viable level.
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 'pairs' parameter is not explained at all. The description lists supported currencies but does not specify the expected format (e.g., 'USD-BRL' vs 'USD' vs 'BRL-USD') or provide examples. With schema description coverage at 0%, the description fails to compensate for this gap.
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 clearly states it provides official closing exchange rates against the Brazilian real (BRL) for a specific list of currencies (USD, EUR, GBP, etc.), with buy and sell rates. This specific verb+resource+scope distinguishes it from siblings like mercado_crypto and mercado_quote.
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 gives clear context: this tool is for FX rates against the real, and it notes weekend/holiday fallback behavior. However, it does not explicitly mention alternative tools (e.g., mercado_crypto for crypto) or when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: authenticate and connect are separate (login vs status), the mercado_* tools each target a specific asset class or function (crypto, currency, listing, macro, quote, ticker search), and platform tools like marketplace, report_bug, show_version, and toolkit_info are unambiguous. There is no meaningful overlap that would cause an agent to select the wrong tool.
The naming is mixed: financial tools consistently use the 'mercado_' prefix, but platform tools use a variety of conventions—single words (authenticate, connect, marketplace), verb_noun with underscores (report_bug, show_version), and nouns (toolkit_info). While readable, this inconsistency is noticeable and not as uniform as a strong verb_noun pattern.
At 12 tools, the count is within a reasonable range, but roughly half of the tools are platform-management concerns (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) rather than financial data. This makes the set feel heavier and less focused than a pure market-data server, though it's not excessive.
The financial data tools cover a broad range: quotes, screening, crypto, exchange rates, macro indicators, and ticker discovery—sufficient for a Brazilian market data server. Some potential gaps like news or portfolio management are out of scope, and the platform tools add extra utility, leaving no critical missing operations for the core purpose.