Conector Juspronto

Buscar no acervo do escritório

buscar_no_acervo

Read-only

Busca textual em TODOS os autos do escritório de uma vez ("onde já enfrentamos essa tese?", "qual precedente interno temos?"). Cada resultado vem com evidenceId pronto para resolver_citacao ou ler_paginas. Acento-insensível; Processo de outro escritório simplesmente não existe aqui. Para buscar dentro de UM processo conhecido, prefira buscar_autos. Devolve total e, quando há mais resultados, proximoCursor: chame de novo com cursor igual a ele para a página seguinte.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "consulta": "<consulta>"
    },
    "name": "buscar_no_acervo"
  }
}

Input Schema

Name	Required	Description
`cursor`	No	proximoCursor da resposta anterior, para a página seguinte (vale por 1 hora; use com a mesma consulta e os mesmos filtros)
`limite`	No	Máximo de resultados por página (padrão 10, teto 20)
`periodo`	No	Janela por data de ajuizamento do processo (opcional)
`consulta`	Yes	Texto a procurar no acervo do escritório
`tipoPeca`	No	Tipo da peça (opcional)
`processoId`	No	Restringir a um processo (opcional)

Output Schema

Name	Required	Description	Default
`aviso`	No
`total`	No
`frescor`	No
`mensagem`	No
`truncado`	No
`resultados`	No
`avisoConteudo`	No
`proximoCursor`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "aviso": {
+      "type": "string"
+    },
+    "avisoConteudo": {
+      "type": "string"
+    },
+    "frescor": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {
+            "andamentosAte": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "atosDepoisDosAutos": {
+              "items": {
+                "additionalProperties": {},
+                "properties": {
+                  "andamentoId": {
+                    "type": "string"
+                  },
+                  "data": {
+                    "type": "string"
+                  },
+                  "descricao": {
+                    "type": "string"
+                  }
+                },
+                "type": "object"
+              },
+              "type": "array"
+            },
+            "autosAte": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "aviso": {
+              "type": "string"
+            },
+            "djenAte": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "truncado": {
+              "type": "boolean"
+            }
+          },
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "mensagem": {
+      "type": "string"
+    },
+    "proximoCursor": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "resultados": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "cnjFormatado": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "evidenceId": {
+            "type": "string"
+          },
+          "pasta": {
+            "anyOf": [
+              {
+                "type": "number"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "processoId": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "type": "number"
+    },
+    "truncado": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedOct 25, 2026

addedInput schema / properties / cursor

Added value: +{
+  "description": "proximoCursor da resposta anterior, para a página seguinte (vale por 1 hora; use com a mesma consulta e os mesmos filtros)",
+  "type": "string"
+}

changedInput schema / properties / limite / description

Previous value: -"Máximo de resultados (padrão 10, teto 20)"New value: +"Máximo de resultados por página (padrão 10, teto 20)"

First observedOct 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, non-destructive and closed-world, but the description adds context they don't carry: accent-insensitive matching, that other firms' cases are simply absent from the corpus, and that each hit carries an evidenceId ready for resolver_citacao or ler_paginas. The pagination contract (total, proximoCursor) is also disclosed, though the output schema already covers return shape, so this is reinforcement rather than new information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Short and front-loaded: scope first, then what results carry, then the corpus caveat, then the alternative tool, then pagination. Every sentence contributes a distinct, actionable fact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a cross-corpus search tool with six parameters and an existing output schema, the description covers everything an agent needs: scope, matching behavior, corpus boundary, hit chaining to sibling tools, alternative tool selection, and the cursor loop.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each parameter (consulta, cursor, limite, periodo, tipoPeca, processoId) is documented in the schema itself. The description only restates the cursor parameter, and adds no semantics for the filters (period window on filing date, piece type) beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with explicit scope: textual search across ALL of the firm's case files at once, illustrated by two realistic queries. It directly differentiates itself from the sibling buscar_autos by naming the condition that selects the other tool (searching inside one known case).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use examples ('onde já enfrentamos essa tese?'), an explicit alternative with its selecting condition ('Para buscar dentro de UM processo conhecido, prefira buscar_autos'), and procedural pagination guidance for the next call. Almost nothing is left to inference.

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

All Conector Juspronto tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?