Busca páginas do acervo jurídico brasileiro por assunto, em português. Devolve caminhos canônicos que servem de entrada para ler_pagina.
| Name | Required | Description | Default |
|---|---|---|---|
| limite | No | máximo de resultados (padrão 8, teto 25) | |
| consulta | Yes | pergunta ou termos em português, como 'produto com defeito troca' |
| Name | Required | Description | Default |
|---|---|---|---|
| paginas | Yes | ||
| veredito | Yes | ||
| total_indexado | Yes |
Changes observed during successful MCP inspections.
Output schema / properties / vereditoAdded value: +{
+ "additionalProperties": false,
+ "properties": {
+ "cobertura": {
+ "additionalProperties": false,
+ "properties": {
+ "exigida": {
+ "type": "integer"
+ },
+ "usada": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "exigida",
+ "usada"
+ ],
+ "type": "object"
+ },
+ "confianca": {
+ "type": "string"
+ },
+ "fuzzy": {
+ "type": "boolean"
+ },
+ "termos": {
+ "items": {
+ "type": "string"
+ },
+ "type": [
+ "null",
+ "array"
+ ]
+ }
+ },
+ "required": [
+ "confianca",
+ "cobertura",
+ "termos",
+ "fuzzy"
+ ],
+ "type": "object"
+}Output schema / requiredPrevious value: -[
- "paginas",
- "total_indexado"
-]New value: +[
+ "paginas",
+ "total_indexado",
+ "veredito"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, and the description reinforces a non-mutating search behavior. It adds valuable behavioral context by disclosing that results are canonical paths meant to feed into ler_pagina. No contradictions with annotations were found.
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 only two sentences, with the main purpose and scope in the first sentence and the key output behavior in the second. Every phrase earns its place, and it is front-loaded with the most decision-relevant information.
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 read-only search tool with two parameters, full schema coverage, and an output schema available, the description is largely complete. It explains what to search, in what language, and how to use the returned canonical paths. The only notable gap is lack of explicit guidance on how this tool compares to sibling search tools, though that is not essential for basic invocation.
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 100%, and the schema already documents both 'consulta' as a Portuguese question/terms and 'limite' as a max results cap with default 8 and ceiling 25. The description's 'por assunto' and 'em português' reinforce the intended query semantics but do not add substantial 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 states a specific verb and resource: 'Busca páginas do acervo jurídico brasileiro por assunto, em português.' It also differentiates itself from sibling tools by specifying that it returns canonical paths intended as input for ler_pagina, which helps an agent distinguish it from buscar_duvidas or buscar_semantico.
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 provides clear context for when to use the tool: searching the Brazilian legal collection by subject in Portuguese and obtaining canonical page paths for later reading with ler_pagina. However, it does not explicitly state when not to use it or mention alternatives such as buscar_semantico, leaving some selection inference to the agent.
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.