Comparar candidatos

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

Goes well beyond the readOnly/idempotent annotations: fixed urna-number ordering, an explicit refusal to rank, score or recommend, a list of fields never returned (CPF, título, birth date, age, gender, race, marital status, schooling), and a note that names/coalitions/links are candidate-declared data rather than instructions. That is unusually rich behavioral and safety disclosure.

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?

One dense paragraph, front-loaded with the core comparison scope before the ordering rules, exclusions and injection warning. Slight redundancy in the triple negative ("não ordena por valor, não pontua e não recomenda voto"), but every sentence carries substantive information.

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 an output schema present, the description need not explain return values, and it covers everything else: selector resolution, default round behavior, ordering guarantee, and privacy exclusions. Nothing an agent needs to call this correctly 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?

Schema coverage is 100%, so the baseline is 3. The description adds genuine meaning by explaining that numbers and sq_candidatos are interchangeable selectors, that both must resolve to 2-4 entries, and what happens when both are omitted — semantics the schema only hints at.

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 and resource ("Compara lado a lado de 2 a 4 candidaturas do mesmo cargo, UF e turno") plus the exact fields compared. The scope constraint (2-4 candidacies, same office/UF/round) separates it cleanly from list_candidates and get_candidate without opening any schema.

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?

Gives clear usage conditions and a default path: with neither sq_candidatos nor numbers it compares all candidacies on the urna when there are 2-4 (the runoff case). It does not explicitly name the sibling tools (list_candidates, get_candidate) as alternatives, so routing is implied rather than stated.

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