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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavioral context beyond those annotations: it calculates by summing corrected discount installments and situates the operation within the STF agreement framework. No contradiction with annotations exists.
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 consists of two focused sentences with no filler. It front-loads the core purpose and adds relevant legal and code detail without unnecessary elaboration. Every part earns its place.
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?
The description gives good domain context and a clear sense of the computation, but it leaves gaps: no output format description, no explicit explanation of how 'indice' affects the correction, and no guidance on required versus optional parameters. It is adequate but not fully complete for a tool with no output schema and low schema description coverage.
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 needed to compensate by explaining the parameters. It only loosely relates to 'descontos' by referring to 'parcelas descontadas'. It does not explain the role of 'indice' (despite mentioning 'corrigidas') or 'data_calculo', leaving the agent to infer their meaning from the schema alone.
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 names the operation (restituição de descontos indevidos no INSS) and the specific resource/domain, including the exact associative fraud codes (280/304/310/378). It states what the tool does: sum corrected discounted installments. This strongly distinguishes it from sibling calculation tools by domain and legal basis.
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 when to use the tool: when handling undue INSS discounts and administrative restitution via the STF agreement (ADPF 1.236). However, it does not explicitly state when not to use it or mention alternatives among the many sibling calculation tools, leaving routing partially to inference.
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 16 calculation tools are each tied to a distinct legal scenario (rent, criminal sentencing, FGTS, labor severance, etc.), so misselection is unlikely. However, the platform meta-tools overlap: connect, toolkit_info, and authenticate all deal with connection/auth state, and marketplace's list_tools/describe overlaps with toolkit_info.
The legal calculators use a consistent calculo_<domain> prefix, which is highly predictable. But the six meta-tools use standalone English names (connect, marketplace, report_bug) and the prefix itself mixes nouns (calculo_aluguel) with a verb (calculo_atualizar), so the overall convention is not uniform.
22 tools is on the heavy side for a server claiming to be about 'juros e multa', especially since six tools are unrelated platform administration features. The 16 legal calculators are arguably well-scoped, but the meta-tool wrapper inflates the count and blurs the server's purpose.
The legal calculation surface is unusually broad: civil, criminal, labor, social security, banking, and family law are all represented, and the calculo_atualizar tool provides the generic debt-update/interest/fee calculation implied by the server name. Minor gaps exist—there is no dedicated simple-interest-only calculator or court-fees/custas calculator—but no obvious dead-end workflows remain.