Consulta a situação da CNH (Carteira Nacional de Habilitação) pelo CPF do próprio condutor em base oficial: número de registro, categoria, validade e situação. É a mesma informação que o titular acessa nos canais oficiais (SENATRAN/DETRAN) para acompanhar a própria habilitação. Não expõe dado sigiloso de terceiros.
| Name | Required | Description | Default |
|---|---|---|---|
| CPF | Yes | ||
| completo | 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 read-only and idempotent hints. The description adds context that the data comes from official SENATRAN/DETRAN channels and is the same as the owner accesses, plus a privacy guarantee. No contradictions with 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?
Two sentences with no filler. The main verb and resource are front-loaded, and each sentence adds essential scope or privacy context.
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 simple query with two params, no output schema, and strong annotations, the description adequately covers purpose, scope, and data source. The main gap is the unexplained 'completo' parameter, which prevents a perfect score.
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 has 0% coverage and the description does not explain the optional 'completo' parameter. While CPF is implied, the 'completo' boolean is left ambiguous, and the description does not detail how it affects the query or response. The description only lists output fields, not parameter behavior.
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 clearly states the tool queries the CNH status by CPF, listing the specific fields (registration number, category, validity, situation). It distinguishes from sibling tools about vehicle fines and history by focusing on the driver's own license.
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?
It indicates it's for the driver's own CPF and explicitly notes it does not expose third-party confidential data, implicitly telling agents not to use it for others' information. However, it lacks explicit comparison to sibling tools like 'multas_veiculos_proprietario'.
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 five multa-related tools are clearly distinct by resource (vehicle debts, history, federal infractions, CNH points, vehicles by owner), but the platform-level tools overlap: authenticate/connect/toolkit_info all touch connection/auth status, and marketplace bundles many separate capabilities into one broad tool. This creates some boundary confusion for an agent selecting between them.
Domain tools follow a consistent 'multas_' prefix pattern, but utility tools use inconsistent English verb/noun styles: authenticate, connect, marketplace, report_bug, show_version, toolkit_info. Mixing Portuguese noun-phrase names with generic English imperative/descriptive names makes the set feel disjointed and pattern-less.
Eleven tools is within a reasonable range, but it feels top-heavy because only five tools actually serve the core fines-consulta domain while the rest are platform/account/admin utilities. The huge marketplace tool also compresses many sub-operations into one entry, making the count misleading.
The core query workflow is covered: find vehicles by owner, query vehicle debts by plate, check federal infractions, and verify CNH points. Missing features like fine payment or appeal detail are beyond the stated consulta purpose, so there are only minor workaround-level gaps for the apparent scope.