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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the bar is lower; the description still adds substantial behavior beyond that: vintage semantics (coletadoEm vs referencia), the source ignoring $count, the mandatory filter for query completion, and the disabled microdata by confidentiality risk. These are operational constraints and behavioral traits an agent could not infer from annotations or schema. No contradiction 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?

The description is long, but every sentence adds information: purpose, output fields, usage rules, exclusions, defaults, and source quirks are each covered in distinct blocks. It is front-loaded with the core purpose and returns, and the structure makes the density manageable. It is slightly verbose for a mature reader, but there is no fluff or tautology.

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?

Given the tool has 5 optional parameters, an output schema, and a sibling set with overlapping domains, the description is remarkably complete. It covers selection criteria, exclusions, default behavior, output fields, and source limitations, including the reason for the mandatory filter and the vintage interpretation. An agent has enough context to select, invoke, and interpret results correctly without further research.

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 meaningful semantic detail: it explains the reuniao format (R1/2026 = 1ª reunião), clarifies that date parameters refer to the coleta window with a 30-day default, and relates the `base` output to the top5 parameter (consenso vs top5). It also explains `referencia` as the meeting target, connecting the reuniao parameter to the output. This goes beyond the schema's raw descriptions, though the schema already covers the basic syntax.

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 identifies the resource (Focus expectations for the Selic rate) and the organizing axis (Copom meeting, format R1/2026). It explicitly differentiates itself from siblings: 'É separada de bcb_focus_expectativas porque o eixo temporal é a reunião do Copom, não o calendário' and points to bcb_serie_valores for realized Selic. The verb 'Consulta' plus the resource and distinguishing format leave no ambiguity.

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 provides explicit 'Quando usar' and 'Quando NÃO usar' sections, naming bcb_focus_expectativas as the alternative for annual calendar-year expectations and bcb_serie_valores for realized Selic. It also gives concrete example use cases like 'o que o mercado espera da Selic na próxima reunião'. This is the strongest possible usage guidance: when to use, when not to use, and which alternatives to select.

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