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 declare readOnlyHint, idempotentHint, and non-destructiveness. The description adds useful behavioral context beyond annotations: it compares inflation index vs TR per deposit, applies 3% a.a. interest, and notes that deposits can currently be entered manually with OCR planned in the future. No contradiction with annotations.
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 a single dense sentence that front-loads the legal thesis and calculation method, then clarifies the input mode and future OCR roadmap. There is no filler or repetition.
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 legal-calculation tool with no output schema and 0% schema description coverage, the description conveys purpose, methodology, and main inputs well. Still, it leaves gaps around `data_calculo`, the exact structure of each deposit object (competencia/valor), and what the returned calculation object looks like.
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 partially does: 'por depósito' and 'depósitos manuais' clarify `depositos`, 'juros de 3% a.a.' clarifies `incluir_juros_3aa`, and the inflation-vs-TR comparison relates to `indice`. However, `data_calculo` is not explained at all, and the indice enum choices are not mapped beyond the headline 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 uses a specific verb phrase ('calcula a diferença') tied to a concrete resource (FGTS correction under the STF TR→INPC/IPCA-E thesis) and states the per-deposit calculation method. This is distinct enough from sibling generic calculo_* tools to be unambiguous.
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 gives clear context: it is for FGTS revision comparing inflation-index correction with TR and applying 3% a.a. interest, and it explicitly mentions manual deposits as the accepted input mode. It does not name alternative tools or state exclusions, but the legal and domain context makes the appropriate use fairly clear.
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.
Most calculo_* tools are separated by legal scenario, but several overlap in the generic task of correcting overdue amounts with indices and interest (calculo_atualizar, calculo_aluguel, calculo_pensao, calculo_fgts, calculo_restituicao_inss, calculo_rmc_rcc). Platform tools also overlap: connect and toolkit_info both report connection status, so an agent could easily misselect for a generic monetary-correction request.
The calculation tools follow a strong calculo_<area> pattern and platform tools use simple English verbs, with consistent snake_case throughout. The main inconsistency is the mix between Portuguese calculation names and English platform verbs, plus grammatical variation such as calculo_atualizar versus calculo_indice versus calculo_salario_minimo.
22 tools is already on the heavy side, but the bigger issue is scope: the server is named 'Revisão de Contrato Bancário' yet only a few tools are actually banking-contract related. Most calculators target unrelated legal domains like criminal sentencing, divorce, labor, FGTS, INSS, and the marketplace/admin tools add further unrelated surface area.
For a banking-contract-review server, the set lacks obvious companions such as tariff/fee analysis, detailed financing scenario comparison, insurance/consignment breakdowns, or full settlement-planning support. The many unrelated calculators do not fill the gaps in the core banking domain.