Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only/idempotent profile, and the description adds substantial behavior beyond them: every data-returning query debits the balance per the price table, insufficient balance yields HTTP 402, and `requisicoes_usadas: null` means measurement unavailable, not zero. It also pre-empts misreading legacy plan limit/reset fields as a cap.

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 core definition and the field semantics are front-loaded, and each sentence carries a distinct caveat rather than restating the name. It is dense with parentheticals and defensive warnings, making it heavier than an average zero-argument tool needs, but little is genuinely redundant.

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?

With no parameters and no output schema, the description carries full burden and delivers: it explains the unit of `saldo_milesimos`, why zero does not mean empty, what legacy limit/reset fields do not mean, the cost per call, the 402 failure mode, and the null sentinel.

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 tool takes zero parameters, so there is nothing to disambiguate in the schema. The description instead spends its effort on returned-field semantics (milésimos units, welcome balance excluded), which is valuable but is not parameter documentation.

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?

States a concrete verb+resource (returns balance and month usage of the connected account) and names the exact fields involved. It explicitly rules out the biggest confusion risk in this sibling set: 'É sobre o consumo da API, NÃO sobre consumo de combustível do veículo', separating it from carpedia_custo_uso and carpedia_relatorio_consumo.

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?

Clear about the context of use (checking prepaid credit and monthly request volume) and states what the tool cannot do: there is no MCP tool to create or top up balance, directing the agent to the panel or API v2 instead. It does not explicitly route to/away from carpedia_status_credito or carpedia_lancamentos, which would have completed the picture.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.