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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description adds beyond that: it states the implementation is a live GET against the public IBGE SIDRA API, returns Markdown plus structuredContent, and discloses that in statistics mode campos/formato are ignored and registros comes empty. 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 block earns its place: a front-loaded purpose sentence, grouped indicator catalog, compact examples, statistics-mode rules, sibling routing, and a one-line behavior note. Markdown headings and bullet lists make it skimmable rather than a wall of text.

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 10-parameter, 0-required tool with an output schema, the description is complete: indicator vocabulary, statistics/grouping semantics, exclusions in stats mode, alternatives, and API/response behavior are all covered. The remaining parameters (localidades, categoria, topN) are adequately documented in the schema, so nothing needed for correct invocation is missing.

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?

With 100% schema description coverage, the baseline is 3, but the description adds substantial value: it enumerates valid indicador values with meanings, clarifies estatisticas=true semantics (full distribution, top/bottom over all rows before truncation), explains agruparPor ranking behavior, and illustrates periodos and nivel_territorial usage. This is exactly the kind of semantic information an agent needs beyond 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?

Opens with a specific verb and object — 'Queries IBGE economic and social indicators' — then names all available indicators grouped by category. The 'Use a different tool when' section explicitly contrasts ibge_comparar, ibge_censo, and ibge_cidades, so an agent can discriminate it from siblings.

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?

Provides explicit routing guidance: use a different tool for locality comparison, census themes, or single-municipality panels. It also gives concrete parameter examples (indicador, periodos, nivel_territorial, estatisticas) and a clear condition for statistics mode, leaving no ambiguity about when this tool is appropriate.

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