Progressão de regime (LEP art. 112, Lei 13.964/2019): percentual de cumprimento por primário/reincidente × comum/hediondo × violência/resultado morte, descontando remição (trabalho/estudo) e detração, e retorna a data de progressão.
| Name | Required | Description | Default |
|---|---|---|---|
| hediondo | No | ||
| pena_anos | Yes | ||
| violencia | No | ||
| reincidente | No | ||
| horas_estudo | No | ||
| dias_detracao | No | ||
| resultado_morte | No | ||
| dias_trabalhados | No | ||
| inicio_cumprimento | Yes |
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 destructiveHint:false, so the safety profile is covered. The description adds behavioral context by describing how the percentage is computed (primário/reincidente, comum/hediondo, violência/resultado morte) and that remição and detração are deducted before returning the progression date. It does not disclose output structure or edge cases, but the core behavior is visible.
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?
One dense sentence front-loads the legal basis and calculation logic and stops after the output. Every clause adds information, with no filler or repetition of the schema.
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 9-parameter calculator with no output schema, the description is adequate but incomplete: it states the main factors and the returned value, but omits the output format, date input format, and any limitations or assumptions about the legal requisitos. An agent would need to inspect parameter names or make reasonable guesses.
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 compensates by mapping the parameters to legal concepts: reincidente, hediondo, violencia, resultado_morte, horas_estudo/dias_trabalhados (remição), and detração. However, it does not explicitly explain the date format for inicio_cumprimento or the exact meaning of every numeric parameter, leaving some inference to the property names.
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 names the specific legal calculation (prison regime progression under LEP art. 112, Lei 13.964/2019), identifies the relevant factors, and states that it returns the progression date. This clearly distinguishes it from sibling calculators like calculo_dosimetria or calculo_trabalhista.
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 intended scenario is strongly implied by the legal reference and formula, but there is no explicit when-to-use/when-not-to-use guidance or comparison with sibling tools. An agent would have to infer that it is for progressão de regime rather than, say, dosimetria da pena.
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 mostly distinct by legal domain, but calculo_atualizar is a generic monetary-correction tool that overlaps with correction logic built into calculo_pensao, calculo_aluguel, and calculo_fgts. The platform tools like connect and toolkit_info are distinct but sit awkwardly alongside the calculators.
The legal calculators consistently use a calculo_ prefix in snake_case, but suffixes mix verbs, nouns, adjectives, and acronyms. The six meta tools break the pattern entirely with bare names like connect, marketplace, and report_bug.
22 tools is already on the heavy side, but the scope mismatch is severe: a server named 'Cálculo de Pensão Alimentícia' exposes 16 calculators for unrelated legal areas plus 6 platform administration tools. Only calculo_pensao directly matches the server name, making the count feel inflated and unfocused.
For the stated child-support purpose, the surface is incomplete: calculo_pensao covers only arrears and lacks clear support for prospective alimony calculation, modification/review, or enforcement scenarios. If viewed as a general legal calculator suite, it is broad but still has notable gaps, and the narrow server name makes those gaps more glaring.