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

The annotations already declare read-only, idempotent, and non-destructive behavior, and the description adds substantial behavioral detail on top: the underlying formula, per-spouse quota, torna for imbalance, and the ability to override the regime default through entra_partilha. This goes far beyond the annotation booleans.

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 compact and efficient: two sentences deliver the purpose, formula, output concept, and a usage tip with no filler. The most important scoping information appears first, and the actionable override instruction is cleanly separated at the end.

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 tool with nested arrays, four parameters, no output schema, and no property descriptions, the high-level formula and override rule are useful but incomplete. It does not explain how each regime maps to the legal flags or what the result structure looks like, though the clear domain and self-explanatory Portuguese field names reduce the risk.

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%, but the description does give meaning to the main parameters: regime selects the legal rule, bens and dividas feed the mass calculation, and entra_partilha overrides defaults. However, several nested legal flags such as oneroso, heranca_doacao, adquirido_na_constancia, anterior_casamento, incomunicavel, and titular are left unexplained, so an agent must rely on field names and legal background.

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 is specific and domain-rich: it states the tool computes divorce asset division under a Civil Code property regime, including shareable mass, each spouse's quota, and equalization payment. This clearly differentiates it from sibling calculo_* tools such as pensao, FGTS, and trabalhista, which address different calculation domains.

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 provides clear application context: use for divorce asset partition when a Civil Code regime applies, and it explains how to override the default inclusion of assets via entra_partilha. It does not explicitly name excluded cases or compare with alternatives, but the intended use is obvious enough that an agent can choose it without confusion.

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