Skip to main content
Glama
elpabloultron

Open Legal Chile

by elpabloultron
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

caso_analizar

Analyze a Chilean legal case file or documents to identify the matter and return a plan: which tools to run, in what order, and what is missing to continue.

Instructions

Usala SIEMPRE que la persona pida analizar un caso, una carpeta de expediente, un expediente, unos documentos o 'este caso', aunque no nombre ninguna herramienta: frases como «¿podés analizar esta carpeta?», «analizame el caso de Ailin», «¿por dónde empiezo con esto?» o «mirá estos documentos y decime de qué se trata» son exactamente su entrada. Devuelve un PLAN: de qué se trata, qué herramientas usar y en qué orden, y qué falta para poder avanzar. No modifica nada ni consulta servicios externos: sólo lee lo que le pasás. La materia la decide con reglas (Rol/RIT y palabras clave chilenas), no adivinando; si no alcanza la información, lo dice.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tipoNocómo interpretar la entrada (por defecto se deduce)
entradaYesruta de la carpeta o del archivo, o el texto mismo
consultaNola pregunta u objetivo, para que el plan apunte a eso
estudio_completoNoSi es True, realiza en un solo paso local el análisis, consulta de marco normativo BCN y doctrina FTS5, consolidando la respuesta sin turnos adicionales

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.6.5
    • addedInput schema / properties / estudio_completo
      Added value: +{
+  "description": "Si es True, realiza en un solo paso local el análisis, consulta de marco normativo BCN y doctrina FTS5, consolidando la respuesta sin turnos adicionales",
+  "type": "boolean"
+}
  2. Addedv1.6.4

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses a great deal: it returns a plan, does not modify anything, does not consult external services, only reads input, decides the legal subject by rules rather than guessing, and says so when information is insufficient. The only caveat is that the absolute claim 'no consulta servicios externos' sits uneasily beside the estudio_completo parameter's mention of a BCN normative query, which may be local or external; this slight ambiguity prevents a 5.

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

Conciseness4/5

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

The instruction is front-loaded with the trigger condition and examples, and every clause adds information: output type, side effects, and matter-determination rule. It is long but not wasteful; a little more paragraph separation would improve scannability.

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

Completeness4/5

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

Without an output schema, the description adequately specifies the return as a PLAN with components (what it is, tools/order, gaps), and it covers triggers, side effects, and the honesty rule for insufficient information. It does not describe the effect of estudio_completo, but the schema already covers that parameter.

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 coverage is 100%, so the baseline is 3 and the description does not need to document each parameter. It reinforces entrada as the input to read and hints at deduction behavior for tipo, but it adds little specific meaning about consulta or estudio_completo beyond the schema.

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?

The description opens with a specific trigger condition ('Usala SIEMPRE que la persona pida analizar un caso...'), lists concrete example phrases, and defines the resource and output ('Devuelve un PLAN...'). It also distinguishes itself from likely siblings by stating it does not modify anything and returns a plan, so an agent can separate it from analysis/execution tools like caso_ejecutar or pjud_analizar_sentencia.

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

Usage Guidelines4/5

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

It gives explicit when-to-use guidance ('Usala SIEMPRE que...') and includes varied phrasings to catch implicit requests, even when no tool is named. It does not name alternative tools or explicit when-not-to-use conditions, but the examples and 'No modifica nada...' effectively rule out mutation/execution tools.

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

Deploy Server

Other Tools