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 the tool read-only, idempotent, and non-destructive. The description adds meaningful behavioral context beyond that: it works 'por depósito', accepts manual deposits, mentions the roadmap for OCR statement input, and specifies the interest component. This goes beyond the structured 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 concise and front-loaded with the purpose, followed by the calculation logic and input mode. It uses two sentences with no filler. Slight awkwardness in the noun-phrase opening and the parenthetical roadmap prevents a perfect score.
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 calculation tool with 4 parameters, no output schema, and 0% schema description coverage, the description conveys the core algorithm and input mode but omits the return format, the role of 'data_calculo', and whether the 3% interest is applied by default. These are meaningful gaps for an agent trying to invoke it correctly.
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 by clarifying 'depósitos' as manual deposits and naming inflation indices and 3% a.a. interest, which maps to 'indice' and 'incluir_juros_3aa'. However, it does not explain 'data_calculo' or the format/behavior of the required 'depositos' array beyond what the schema already shows.
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 identifies a specific verb ('calcula'), a specific resource (FGTS correction), and the exact calculation (difference between inflation-index correction and TR correction, plus 3% a.a. interest). This clearly distinguishes it from the many other 'calculo_*' sibling tools.
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 contextual clues—FGTS, TR-to-INPC/IPCA-E thesis, STF—that imply when the tool should be used. However, it does not explicitly state when to use this tool instead of alternatives like calculo_indice or calculo_revisional, nor does it mention any exclusions or prerequisites.
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 each target a distinct legal area (labor, FGTS, alimony, sentencing, INSS, etc.), and detailed descriptions clarify their boundaries. Some relationship exists among correction/index-based calculators, but the legal context makes them distinguishable. The platform tools are also separate from the domain calculators, though marketplace is broad.
All 16 calculation tools follow a consistent `calculo_<area>` snake_case pattern, which is good. However, the six platform/admin tools use a different style and language (authenticate, connect, marketplace, report_bug, show_version, toolkit_info), creating a clear split between the two clusters.
At 22 tools, the set is on the heavy end. The 16 legal calculators each earn their place for a broad Brazilian legal-calculation suite, but the additional platform and marketplace plumbing tools inflate the count and make the server feel less focused.
The tool surface covers a wide range of Brazilian legal calculation needs: labor, FGTS, criminal sentencing, prison progression, INSS benefits, alimony, divorce, banking revisions, and monetary correction. Minor gaps exist, such as dedicated overtime or additional-hours calculators, but the core workflows are well covered with no obvious dead ends.