Pensão alimentícia em atraso (art. 528 CPC): por mês do período calcula o devido (% do salário mínimo do mês, valor fixo ou % da remuneração), subtrai pagamentos e aplica correção (INPC) + juros 1% a.m. desde cada vencimento.
| Name | Required | Description | Default |
|---|---|---|---|
| forma | Yes | ||
| juros | No | ||
| indice | No | ||
| fim_atraso | Yes | ||
| pagamentos | No | ||
| referencia | Yes | ||
| data_calculo | No | ||
| remuneracoes | No | ||
| inicio_atraso | Yes |
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?
With readOnlyHint, idempotentHint, and destructiveHint already covering the safety profile, the description adds real algorithmic transparency: per-month due computation, payment deduction, INPC correction, and 1% monthly interest from each due date. It does not explain how an explicit `indice` parameter interacts with the stated INPC default, but the core behavior is clear.
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 with no filler; the legal context is front-loaded and every clause adds calculation detail. It is not broken into sections, but it is appropriately compact for a calculation tool.
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?
Given no output schema and 9 parameters with zero schema descriptions, some gaps remain: the return format is not stated, and `referencia` and `data_calculo` are not explicitly explained. The algorithm is well summarized, so the description is adequate but not fully complete for all invocation details.
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?
At 0% schema coverage, the description carries the burden and mostly compensates: it explains the `forma` enum (percentage of minimum wage, fixed value, percentage of remuneration), `pagamentos` (subtracted), `juros` (1% monthly), the period parameters, and `remuneracoes`. It leaves `referencia` and `data_calculo` implicit, but the calculation modes imply the role of `referencia`.
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 that the tool calculates overdue alimony under art. 528 CPC and specifies the three calculation modes. The phrase 'pensão alimentícia em atraso' distinguishes it from the many sibling cálculo tools without needing to inspect their schemas.
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 a clear triggering context — overdue alimony under art. 528 CPC — and what the calculation covers. It does not explicitly name alternatives or state when not to use it, but the domain label is specific enough to route an agent correctly.
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.
The calculo_* tools are largely distinct by legal scenario, but several overlap in mechanics—calculo_atualizar, calculo_pensao, calculo_restituicao_inss, and calculo_rmc_rcc all apply correction and interest to overdue amounts. Platform tools also blur boundaries: authenticate/connect both deal with credentials, and marketplace/toolkit_info both describe installation state.
The 16 calculation tools consistently follow a calculo_<domain> snake_case pattern, which is good. However, the 6 platform tools break the convention with single verbs/nouns (connect, marketplace, authenticate) and mixed forms (report_bug, show_version, toolkit_info), creating two inconsistent naming styles within one server.
22 tools is at the high end of reasonable for a legal-calculation suite, but the server name 'Cálculo de FGTS' suggests a much narrower scope. The platform-management tools add bulk and make the set feel broader and heavier than the name implies.
As a Brazilian legal calculation toolkit, the coverage is strong: labor, pension, criminal sentencing, family, banking, FGTS, and monetary correction are all represented. Minor gaps exist—such as no OCR extraction for FGTS statements and no standalone interest-only calculation—but the core calculation workflows are not dead-ended.