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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: results come from the 'última versão coletada do arquivo de resultado do TSE', disclosing that freshness is bounded by collection time — a real trait for an election-results tool. It stops short of explaining partial-count semantics (e.g. when 'seções totalizadas' is less than the total).

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?

A single sentence, front-loaded with the metric list and ending with scope and provenance. Dense but nothing is wasted; the parenthetical enumeration earns its place by doubling as a return-value preview.

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 metric list usefully substitutes for a return-value description, and the provenance clause covers freshness. But with 7 fully optional, 0%-documented parameters, the description leaves major ambiguities: what happens when nothing is supplied (country-wide default?), what turno selects, what codigo identifies, and which offices are supported. That is short of complete for a tool of this parameter surface.

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 0%, so the description must compensate, and it partially does: 'numa UF', 'num município' and the 'Brasil/UF/município' scope map onto uf, municipio and nivel. But ano, turno and codigo are entirely unaddressed, and critically the cargo restriction (only presidente/governador) is invisible — an agent could reasonably try 'senador' or 'prefeito' and fail.

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 names the resource precisely (official per-candidate election totals) and enumerates the returned metrics (votes, % of valid votes, blank/null, turnout, abstentions, totalized sections), plus the geographic scope (Brazil / UF / municipality) and source (latest collected TSE results file). It does not, however, explicitly distinguish itself from siblings like eleicoes_consultar_secao or eleicoes_comparar_turnos, leaving the agent to infer the boundary.

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?

It states the aggregation scope but gives no when-to-use or when-not guidance, and never names an alternative tool. With siblings such as eleicoes_consultar_secao (section-level) and eleicoes_comparar_turnos (turn comparison) present, an explicit routing sentence was needed.

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