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

Annotations already declare readOnly/idempotent/non-destructive, so the description is free to add real behavioral content: it computes per-field subtractions and cross-checks that the variations sum to the electorate variation, and it explicitly refuses interpretation. That tells the agent what the output will contain and that no narrative analysis is produced.

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 dense sentence that front-loads the operation and then the scope options and the arithmetic guarantee. Every clause carries information; only the paragraph-length density keeps it short of a 5.

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 6-parameter tool with no output schema and zero schema descriptions, the definition conveys the concept and output shape but not the parameter contract or how required/optional fields interact. It is enough to understand the tool, not quite enough to call it correctly on the first try.

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% across 6 parameters, and the description only alludes to geography levels without mapping them to parameter names, formats, or value types. It never mentions 'ano', 'zona', or 'cargo' (the only enum), and it advertises Brazil-level totals even though 'uf' is required — leaving real ambiguity about how to scope a national comparison.

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 operation (compare 1st and 2nd round side by side) plus the aggregation levels it supports (Brazil, UF, municipality, section) and the derived fields (2nd − 1st per field). This clearly separates it from listing tools like eleicoes_totais, though no sibling is named explicitly.

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?

Usage is implied by the enumerated scopes ('do Brasil, de uma UF ou de um município ... ou de uma seção') and by the closing 'Sem interpretação', which signals a raw-numbers tool. There is no explicit when-to-use/when-not or pointer to eleicoes_totais or eleicoes_consultar_secao as alternatives.

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