Partilha de bens no divórcio por regime (Código Civil): apura a massa partilhável (bens − dívidas conforme o regime) e a quota de cada cônjuge, com torna por desequilíbrio. Marque entra_partilha por bem para sobrepor o default do regime.
| Name | Required | Description | Default |
|---|---|---|---|
| bens | Yes | ||
| nomes | No | ||
| regime | Yes | ||
| dividas | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (read-only, idempotent, non-destructive), the description discloses the calculation behavior: shareable mass equals assets minus debts according to regime, spouse shares, and compensation for imbalance. It also reveals the override mechanism for 'entra_partilha', which is important behavioral and semantic context.
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?
Two sentences, front-loaded with the tool's purpose and formula, with the override instruction as a compact second sentence. Nothing is redundant and every clause earns its place.
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 complex legal calculator with no output schema, it does enough: it describes inputs (assets/debts/regime), the computation, and the outcome (shareable mass, quotas, compensation). It does not enumerate the per-regime defaults or define each legal flag, but the override instruction plus schema enums make invocation feasible.
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 compensate. It does add meaning for 'bens', 'dividas', 'regime', and 'entra_partilha' by embedding them in the formula and override instruction, but it does not explain fields like 'titular', 'incomunicavel', or 'nomes', leaving some parameters to be inferred from schema enum names and structure.
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 states a specific verb and resource: it 'apura a massa partilhável' for 'partilha de bens no divórcio por regime', including each spouse's share and compensation. This level of specificity clearly separates it from sibling tools like calculo_fgts or calculo_pensao.
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 gives clear context: use for divorce asset division under a Civil Code property regime, and tells the agent to mark 'entra_partilha' per asset to override the default. It does not explicitly name alternative tools or state when not to use it, but the domain context is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each calculo_* tool targets a distinct legal/financial area (rent, alimony, FGTS, criminal sentencing, etc.), and their descriptions cite specific statutes that make the purpose clear. The only mild ambiguity is that calculo_atualizar and calculo_indice both handle generic monetary correction, while some INSS/FGTS tools share 'refund plus correction' semantics, but the specialized names avoid serious confusion.
The 16 domain tools follow a consistent 'calculo_<topic>' snake_case pattern, but calculo_atualizar uses a verb where the rest use nouns. The six platform tools break the pattern entirely with short English names (authenticate, connect, marketplace, report_bug, show_version, toolkit_info), resulting in two readable but distinct naming conventions.
At 22 tools, the set is in the heavy range, and while the 16 legal calculators each justify their place, the six unrelated MCP platform utilities bloat the count for a server named 'Atualização Monetária'. The breadth of the legal calculators makes this borderline rather than excessive, but the overall scope is less focused than a well-scoped 10-15 tool server.
The toolkit covers a remarkably wide set of Brazilian legal calculations: monetary correction, index factors, alimony, labor severance, FGTS, INSS refunds, bank contract revisions, criminal sentencing, prison progression, family division, retirement benefits, and contribution time. Minor gaps exist, such as no standalone general-interest calculator and no OCR for FGTS statements yet, but agents can work around these with the generic tools.