Correção do FGTS (tese TR → INPC/IPCA-E, STF): por depósito calcula a diferença entre corrigir pelo índice de inflação vs pela TR, com juros de 3% a.a. da conta. Aceita depósitos manuais (ou, futuramente, extrato OCR).
| Name | Required | Description | Default |
|---|---|---|---|
| indice | No | ||
| depositos | Yes | ||
| data_calculo | No | ||
| incluir_juros_3aa | 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?
Annotations already mark this read-only and idempotent, and the description adds useful behavioral context: per-deposit granularity, the specific 3%-per-year interest assumption, and the TR-to-inflation comparison logic. It does not describe return format or edge cases, but the core calculation behavior is transparent enough.
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 two concise sentences with no fluff. The main computation is front-loaded, the input limitation is stated, and the future OCR note adds useful context without bloating the text.
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 no output schema and four parameters, the description gives the core calculation logic and input mode but omits the output shape, default behavior of incluir_juros_3aa, and how deposits should be structured. It is adequate for a high-level understanding but leaves practical invocation details unresolved.
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, but it only partially does. It explains the inflation-vs-TR concept and 3% interest, which relates to indice and incluir_juros_3aa, yet it does not explain the structure of depositos, the role of data_calculo, or the full list of supported indices.
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 clearly states the tool calculates the FGTS correction difference per deposit, comparing inflation indices against TR and applying 3% annual interest. This specific verb+resource+computation distinguishes it from generic sibling tools like calculo_indice or calculo_trabalhista.
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?
The description implies usage for FGTS correction calculations from manual deposits and notes OCR extraction is only future functionality. However, it never explicitly says when not to use this tool or names alternative sibling tools for related calculations.
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.