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-destructive behavior. The description adds useful behavioral context: the calculation is per deposit, applies 3% a.a. interest, and currently accepts manual deposits only, with OCR mentioned as future capability. It does not detail return shape or edge cases, but it adds value beyond the annotations without contradicting them.
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 compact: two sentences with the essential purpose front-loaded and the OCR limitation in a parenthetical. Every phrase contributes information, and there is no repetition of schema or annotation content.
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 4-parameter calculation tool with no output schema, the description covers the core computation and main inputs but omits the output shape and the role of `data_calculo`; default index behavior is also implied rather than stated. The annotations reduce the need for side-effect disclosure, but an agent would still have to infer some invocation details.
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 alludes to the `indice` choice ('índice de inflação vs TR'), the `depositos` list ('por depósito', 'depósitos manuais'), and interest behavior ('juros de 3% a.a.'). However, it does not clarify `data_calculo`, the structure of `competencia`/`valor`, or default behavior when optional parameters are omitted.
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 opens with 'Correção do FGTS (tese TR → INPC/IPCA-E, STF)', which immediately identifies the specific subject and legal context. 'Por depósito calcula a diferença' states the precise computation, making it clearly distinguishable from sibling calculation tools like calculo_revisional or calculo_indice.
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 establishes a clear use context: FGTS correction comparing inflation-index correction against TR, with per-deposit granularity. It does not explicitly name alternatives or exclusions, so it stops short of a 5, but the intended invocation scenario 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 16 calculo_* tools are each tied to a specific legal area and are generally easy to distinguish. However, the platform tools overlap: marketplace bundles discovery, auth, listing, and bug-report flows that also exist in authenticate, connect, toolkit_info, and report_bug.
The calculo_* group is highly consistent and readable. The six platform tools follow a different, more mixed English convention with bare verbs, noun phrases, and snake_case names, so the set as a whole has two naming schemas rather than one.
22 tools is in the heavy 16-25 range and feels excessive for a server titled 'Reajuste de Aluguel'. Some legal calculators are useful in a broader legal-calculation platform, but the title and the actual scope are mismatched.
For a broad Brazilian legal-calculation toolkit, coverage is quite wide: rent, monetary updating, criminal sentencing, FGTS, INSS, labor, and banking calculations are present. Still, there are notable gaps for a general legal surface, such as other INSS benefit calculations or civil compensation estimates, and the rent-adjustment title does not represent the full set.