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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, and the description adds genuinely new context: aggregation from boletins de urna, official 2nd-round data only for presidente/governador, and the single-match municipality behavior. The privacy statement (no CPF, birth date or e-mail) is a meaningful addition beyond structured fields.

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 purpose and dense with useful detail; the second sentence on privacy earns its place. The first sentence is long and clause-heavy, which slightly hurts scanability but wastes no words.

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?

With no output schema, the description does the work of describing return contents (party, office, UF, situation, 1st-round votes, top municipalities, 2nd round for executive races). For a read-only lookup tool, an agent has what it needs to call it correctly, with only the 'ano' semantics as a minor gap.

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 description coverage is 0%, so the description must carry the burden. It explains 'termos' (urna name or number) and enumerates the cargo values well, and 'uf' appears implicitly, but the 'ano' parameter is never addressed and the text hardcodes 2026, leaving ambiguity about what that parameter does.

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 (buscar) and resource (candidato) plus the scope: all 2026 offices, looked up by urna name or number. It also enumerates the returned fields (partido, cargo, UF, situação, votos), which clearly separates it from siblings like eleicoes_totais or eleicoes_consultar_secao.

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 implies how to use it (lookup by name or number) and adds a useful conditional note that municipality detail appears only 'quando a busca acha um só'. However, it never names an alternative tool or an explicit when-not-to-use condition, so routing between it and siblings such as eleicoes_totais is left to inference.

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