Skip to main content
Glama

FalaZuki Finance BR

check_severance

Confere um TRCT (termo de rescisão) de empregado CLT verba a verba contra a conta canônica da rescisão, com as tabelas vigentes NA COMPETÊNCIA: saldo de salário, 13º e férias proporcionais (com os avos IMPRESSOS no documento, que mandam sobre a derivação por meses de casa), terço, aviso indenizado (ou trabalhado), multa do FGTS, INSS, IRRF e o líquido total. Cada verba informada recebe veredito (confere, confere com arredondamento, difere com o valor); verba não informada vira referência sem veredito. Recusas honestas: multa sem o saldo do FGTS é não conferível; remuneração variável (médias) recusa a conferência inteira; férias vencidas e outras verbas declaradas tiram o líquido total da comparação. Nunca inventa diferença. Parâmetros obrigatórios: salary, months_worked, type, reference_date. Opcionais: days_worked_in_month, dependents, notice_worked, thirteenth_twelfths, vacation_twelfths, fgts_balance, informed_salary_balance, informed_thirteenth, informed_vacation, informed_vacation_bonus, informed_notice_pay, informed_fgts_penalty, informed_inss, informed_irrf, informed_net_total, has_variable_pay, declared_items. Use exatamente estes nomes, em inglês.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeYesTipo de desligamento
salaryYesSalário bruto mensal fixo, em R$
dependentsNoDependentes para o IRRF
fgts_balanceNoSaldo do FGTS, em R$. Sem ele, a multa fica não conferível
informed_inssNoINSS descontado no TRCT, em R$
informed_irrfNoIRRF descontado no TRCT, em R$
months_workedYesMeses de casa (define os dias de aviso prévio)
notice_workedNoAviso prévio trabalhado: o TRCT não traz aviso indenizado
declared_itemsNoVerbas do TRCT que o motor não reconstrói: expired_vacation (férias vencidas), other
reference_dateYesData da rescisão (competência das tabelas), aaaa-mm-dd
has_variable_payNoRemuneração variável (comissões, HE habituais)? A conferência recusa: médias não são reconstruídas
informed_vacationNoFérias proporcionais no TRCT, em R$
vacation_twelfthsNoAvos das férias como impressos no TRCT; sem ele, derivado dos meses
informed_net_totalNoTotal líquido do TRCT, em R$
informed_notice_payNoAviso prévio indenizado no TRCT, em R$
informed_thirteenthNo13º proporcional no TRCT, em R$
thirteenth_twelfthsNoAvos do 13º como impressos no TRCT; sem ele, derivado dos meses
days_worked_in_monthNoDias trabalhados no mês da rescisão
informed_fgts_penaltyNoMulta do FGTS no TRCT, em R$
informed_salary_balanceNoSaldo de salário no TRCT, em R$
informed_vacation_bonusNoTerço constitucional no TRCT, em R$

TDQS

A4.6/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It openly lists honest refusal conditions: FGTS penalty without fgts_balance is not checkable, variable pay refuses the entire check, and declared items like expired vacation remove the net total from comparison. It also states it never invents differences and specifies verdict types (matches, matches with rounding, differs). This is thorough behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-structured: it starts with the purpose, then explains verdicts and refusal logic, and finally lists parameter requirements. Every sentence contributes to understanding the tool's behavior. While long, it is appropriately sized for the complexity of a 21-parameter severance checker, and the structure is logical, so it earns a 4 rather than a 3.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex tool with 21 parameters and no output schema. The description compensates fully by explaining the verification process, the verdicts, the refusal conditions, the precedence rules for avos, the role of each informed_* parameter, and the required vs optional distinction. An agent has enough information to call this tool correctly without guessing about parameters or behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers all 21 parameters at 100% coverage, so the baseline is 3. The description adds meaningful semantic context beyond the schema: it explains that the avos printed on the document take precedence over derivation from months of service, distinguishes informed_* parameters as values from the TRCT to be verified, and clarifies required vs optional parameters. This is more than the schema descriptions provide, so a 4 is warranted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states it performs a line-by-line check of a CLT employee's TRCT (termination agreement) against the canonical severance calculation using current tables for the reference date. It lists the specific items verified (salary balance, 13th, proportional vacation, bonus, notice pay, FGTS penalty, INSS, IRRF, net total) and the verdicts given. This clearly distinguishes it from sibling tools like calculate_severance (which likely calculates severance amounts) and check_payslip (which checks payslips).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context: it is for verifying a provided TRCT document. However, it does not explicitly exclude alternatives or state when to prefer this over calculate_severance or check_payslip. The context is clear but there are no explicit when-not-to-use directives, so it earns a 4 rather than a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0
Disambiguation2/5

Many tools are clearly distinct, but the set contains several near-identical clusters: calculate_dividend_income_goal and calculate_dividend_yield both answer 'how much capital is needed to reach a dividend income target', and calculate_real_salary, calculate_raise_vs_inflation, and calculate_salary_time_value overlap heavily on salary/inflation comparisons. Generic tools like compare_investments and compare_with_cdb also blur the boundary with the many specific yield calculators.

Naming Consistency3/5

Most tools follow a clear verb_noun snake_case pattern with verbs like calculate_, get_, check_, compare_, and advise_. However, the object language is inconsistent (calculate_ganho_capital_imovel alongside calculate_car_affordability), and can_i_quit_job breaks the command-style pattern with a question.

Tool Count1/5

At 114 tools, the server is extremely over-scoped for an MCP surface; an agent cannot reasonably hold all these options in context. The inclusion of a search_calculator tool to route among the others is a strong signal that the tool set itself needs partitioning.

Completeness4/5

The surface is very comprehensive for Brazilian personal finance: employment, taxes, investments, debt, real estate, vehicles, small business, insurance, and market-data queries are all covered. A few minor gaps exist, such as no dedicated generic boleto-fine calculator or consolidated investment comparison engine, but no core workflow feels badly stranded.

Resources