Simula LCI ou LCA (isentas de IR) com o CDI de hoje do Banco Central e calcula o CDB equivalente: qual percentual do CDI um CDB precisaria pagar pra empatar com a letra no mesmo prazo. Parâmetros obrigatórios: principal, cdi_percent, months. Use exatamente estes nomes, em inglês.
| Name | Required | Description | Default |
|---|---|---|---|
| months | Yes | Prazo em meses (1-360) | |
| principal | Yes | Valor investido em R$ | |
| cdi_percent | Yes | Percentual do CDI que a LCI/LCA paga (ex: 90) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does add useful behavioral context: it says the tool uses 'o CDI de hoje do Banco Central', treats LCI/LCA as IR-exempt, and computes an equivalent CDB rate. It does not state assumptions, return format, or limitations, so coverage is adequate but not rich.
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 sentences with no fluff; the main function and output are front-loaded and the parameter naming reminder is a single clause. Every sentence 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?
For a three-parameter calculator with full schema coverage, the description supplies the missing context: the BC/CDI data source, the tax exemption premise, and the equivalence question being answered. The lack of an explicit output format is a minor gap for this simple numeric calculation.
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?
The input schema already provides 100% coverage with descriptions for principal, cdi_percent, and months, so the description needs little extra. The note 'Use exatamente estes nomes, em inglês' adds a naming/language instruction but no new semantic detail beyond the schema.
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 'Simula LCI ou LCA (isentas de IR)' and defines the tool's output: 'calcula o CDB equivalente' and 'qual percentual do CDI um CDB precisaria pagar pra empatar'. This is specific about action, resource, and result, though it doesn't explicitly name sibling tools or contrast with them, so it loses the top score.
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 makes the intended scenario clear — LCI/LCA simulation with today's BC CDI and CDB equivalence — so an agent can infer when it applies. However, it offers no explicit when-to-use versus alternatives such as compare_with_cdb or calculate_cdi_yield, nor any exclusion criteria.
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.
Many tools are clearly distinct, but the set contains several near-identical clusters: calculate_dividend_income_goal and calculate_dividend_yield both answer 'how much capital is needed to reach a dividend income target', and calculate_real_salary, calculate_raise_vs_inflation, and calculate_salary_time_value overlap heavily on salary/inflation comparisons. Generic tools like compare_investments and compare_with_cdb also blur the boundary with the many specific yield calculators.
Most tools follow a clear verb_noun snake_case pattern with verbs like calculate_, get_, check_, compare_, and advise_. However, the object language is inconsistent (calculate_ganho_capital_imovel alongside calculate_car_affordability), and can_i_quit_job breaks the command-style pattern with a question.
At 114 tools, the server is extremely over-scoped for an MCP surface; an agent cannot reasonably hold all these options in context. The inclusion of a search_calculator tool to route among the others is a strong signal that the tool set itself needs partitioning.
The surface is very comprehensive for Brazilian personal finance: employment, taxes, investments, debt, real estate, vehicles, small business, insurance, and market-data queries are all covered. A few minor gaps exist, such as no dedicated generic boleto-fine calculator or consolidated investment comparison engine, but no core workflow feels badly stranded.
