bcb_focus_referencias

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

Even though annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, the description adds substantial behavioral context: the vintage nature of Focus data, the 'coletadoEm'/'referencia' semantics, the fact that counting is done client-side because the source ignores $count, and that the filter is mandatory because unfiltered queries don't complete. It also discloses partial failure behavior ('Se algum escopo não responder, os demais voltam mesmo assim') and confidentiality limitations. This far exceeds the annotation baseline.

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 it is well-structured into clear sections (purpose, scope definition, when to use, when not to use, return shape, failure behavior, source details, and caveats). While some sentences are dense, each contributes to correct usage and avoids ambiguity. It is not as tight as a two-sentence description, but the complexity of the tool justifies its length.

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 full context: its relationship to sibling tools, the meaning of 'escopo', return structure (including the 'falhas' field for partial failures), source provenance, data vintage semantics, mandatory filter constraints, and confidentiality limits. Even with an output schema present, the description provides additional operational context that an agent needs to select and interpret results correctly.

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%, but the description adds meaning beyond the schema by explaining how 'escopo' maps to the five horizons of bcb_focus_expectativas plus 'selic', and clarifies that 'selic' refers to Copom meetings, not a time horizon. It also explains the behavior of omitting 'escopo' (queries all six and returns everything) vs. providing it (restricts to that scope), which is not evident from the schema alone.

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 states a specific verb and resource: 'Lista, POR ESCOPO, os indicadores e as referências que o Focus efetivamente publica' – it clearly explains what the tool does and names the exact consumers (bcb_focus_expectativas, bcb_focus_selic), distinguishing it from sibling tools. The phrase 'para você usar o texto EXATO' further clarifies its role as a discovery/preparation tool, not a data retrieval 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?

The description explicitly states when to use ('antes da primeira consulta ao Focus, ou quando uma consulta volta vazia') and when not to use ('para os valores das expectativas em si'). It even explains the root cause of empty results (indicator not existing in that scope or reference format mismatch), which is actionable guidance beyond mere context.

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