bcb_focus_selic

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, lowering the bar. The description still adds significant behavioral context: the vintage nature of Focus, the meaning of coletadoEm versus referencia, the fact that $count is ignored (count computed locally), the mandatory filter due to source limitations, and the non-exposure of microdata for confidentiality. No contradictions with 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?

Although long, every sentence carries operational weight: purpose, return statistics, use exclusions, response fields, default window, source attribution, and the vintage data caveat. It is dense but efficient, with no filler or repetition of schema details.

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 five optional parameters, complex temporal semantics, and multiple siblings, the description fully explains the Copom meeting axis, the data collection window, the return structure (including 'base', 'filtro', 'referencia'), and source limitations. An output schema exists, so return values are covered by structured data; no additional enumeration needed.

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 100%, so the baseline is 3. The description adds value beyond the schema by explaining the default 30-day collection window, reinforcing the date format expectations, and clarifying that 'referencia' is the Copom meeting rather than the calendar year. This pushes it slightly above baseline.

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 opens with a specific verb and resource: 'Consulta as expectativas de mercado do Focus para a taxa Selic' and clarifies the organizing axis ('organizadas pela REUNIÃO do Copom'). It explicitly distinguishes this tool from siblings by naming bcb_focus_expectativas (annual calendar) and bcb_serie_valores (realized Selic), and states why it is separate.

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 provides explicit 'Quando usar' ('o que o mercado espera da Selic na próxima reunião') and 'Quando NÃO usar' with named alternatives and even series codes for bcb_serie_valores (432, 1178, 4390). This is exemplary guidance, exceeding the minimum expected.

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