Censo Demográfico

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, so the safety profile is covered. The description still adds real context beyond them: it is a live GET against the public IBGE SIDRA API, it returns Markdown plus a typed structuredContent payload, and statistics mode has side effects (campos/formato ignored, registros left empty) that an agent must anticipate.

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?

Front-loaded with the purpose, then organized under labeled sections (years, themes, examples, statistics mode, alternatives, behavior). It is long and repeats the year list already present in the enum, but the structure keeps it scannable and each section carries distinct routing or mode information.

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 9-parameter tool with an output schema and full annotation coverage, the definition supplies the routing, mode semantics, and example calls an agent needs. The only shortfall is that the in-description theme list is a subset of the schema enum, so an agent skimming only the description could under-estimate available themes.

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 goes further with concrete call examples that show parameter interaction (ano="todos" for a historical series, nivel_territorial="3" for literacy by state, tema="listar" to enumerate tables) and explains that agruparPor ranks groups by descending sum. The description's theme list covers only 9 of the 18 enum values, leaving the rest to the schema.

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?

States a specific verb and resource ('Queries IBGE Demographic Census data 1970-2022') plus the scoping constraint that it works without knowing SIDRA table codes, which is exactly the distinction from ibge_sidra. An agent can tell it apart from siblings without opening the schema.

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?

Contains an explicit 'Use a different tool when' block that routes to four alternatives (ibge_cidades, ibge_indicadores, ibge_comparar, ibge_sidra) with the condition selecting each. It also names the exact question shape ('which municipality had the largest 2022 population?') that triggers estatisticas=true.

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