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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds extensive behavioral context beyond these: automatic selection of the value column based on tipo, the result envelope { tipo, modo, ano, totalLinhas, ... }, ordering of agregado[], the default limite of 100 with truncation aviso, and how estatisticas changes behavior. 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?

The description is long but information-dense, with no filler. It is front-loaded with the core purpose, followed by statistics mode, return structure, and sibling distinction. While slightly dense and could be broken into clearer sections, every sentence earns its place in explaining a complex 8-parameter tool.

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's complexity (8 parameters, multiple modes, statistics behavior, output structure) and the presence of a rich output schema, the description covers essentially everything needed: parameter interplay, return shapes, ordering, defaults, truncation behavior, filtering advice, and sibling differentiation. No critical gaps.

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 baseline is 3, but the description significantly enriches parameter meaning: it clarifies that campo is optional and defaults based on tipo, that modo is ignored when estatisticas=true, how agruparPor ranks groups by descending sum, and the effect of limite truncation. This goes well beyond the schema definitions.

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 states the tool's function: querying the Senate's internal budget execution, covering despesas (expenditures with dotação, empenhado, liquidado, pago since 2013) and receitas próprias (revenues since 2012). It uses a specific verb with resource and explicitly distinguishes itself from the sibling senado_orcamento_parlamentar, making the purpose unambiguous.

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 guidance on when to use this tool versus the alternative senado_orcamento_parlamentar ('não confundir...'), and details when to set estatisticas=true with and without agruparPor. It also advises filtering by ano before requesting detalhe to reduce data volume, giving clear context on usage.

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