Restituição de descontos indevidos no INSS (fraude associativa, códigos 280/304/310/378): soma as parcelas descontadas corrigidas. Ressarcimento administrativo via acordo STF (ADPF 1.236).
| Name | Required | Description | Default |
|---|---|---|---|
| indice | No | ||
| descontos | Yes | ||
| data_calculo | 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 read-only, non-destructive and idempotent. The description adds meaningful behavior beyond that: it sums and applies monetary correction to the discounted installments, and ties the calculation to the STF agreement framework. It doesn't cover edge cases or output details, but the safety profile is already carried by 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?
Two dense sentences, no filler. The scoped purpose and legal context are front-loaded, and both sentences add selection-relevant information.
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?
Despite strong annotations, the tool has no output schema and near-zero parameter descriptions, so the description must cover invocation details. It provides the domain context but not the parameter semantics, correction-index behavior, or return value, making it incomplete for reliable agent invocation.
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?
With 0% schema-description coverage, the description must define the parameters, but it only indirectly refers to the discount list ('parcelas descontadas') and the idea of correction ('corrigidas'). It never explains the 'indice' choices, 'data_calculo', or how 'codigo/competencia/valor' are used, leaving an agent under-informed for invocation.
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 action ('Restituição de descontos indevidos no INSS') with a concrete computation ('soma as parcelas descontadas corrigidas') and scopes it to exact discount codes (280/304/310/378). This clearly differentiates it from sibling calculo_* tools, e.g. calculo_indice or calculo_fgts, even without inspecting schema.
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 provides clear when-to-use context: INSS undue discounts from associative fraud codes and the ADPF 1.236/STF administrative reimbursement pathway. It does not explicitly name alternative tools or state when not to use it, so it misses the top level of guidance, but the use case 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.
The calculo_* tools are largely distinct by legal domain, but several share the same underlying correction/juros mechanics (e.g., calculo_atualizar, calculo_aluguel, calculo_pensao, calculo_trabalhista). Platform tools add further boundary confusion: marketplace includes report_bug, list_tools, and auth-related functionality that overlaps with the standalone report_bug, toolkit_info, and connect tools.
The 16 calculation tools follow a consistent calculo_<domain> pattern, which is good. However, the remaining tools mix bare verbs (authenticate, connect), nouns (marketplace), and verb_noun phrases (report_bug, show_version, toolkit_info), creating two distinct naming conventions within the same server.
At 22 tools, the set is on the heavy side of the borderline range. The domain calculators are individually justified, but adding six platform-level tools — including the very broad marketplace tool — makes the overall surface feel bloated for a server whose apparent purpose is judicial liquidation calculation.
The calculation tools cover a wide range of judicial liquidation scenarios: general debt updating, rent, alimony, labor, FGTS, bank contract revision, INSS restitution, RMC/RCC, criminal sentencing, prisoner progression, pension RMI, contribution time, and asset division. Minor gaps exist — such as a dedicated standalone honorários calculator or a more explicit precatório/RPV tool — but calculo_atualizar largely covers general monetary updating.