Skip to main content
Glama

Auditar texto de compliance de IA

gobernador_audit_text
Read-onlyIdempotent

Audits AI system descriptions against Chilean Law 21.719, ISO/IEC 42001, and EU AI Act. Returns non-compliance findings with references and guidance.

Instructions

Analiza una descripción de un sistema de IA o flujo de datos y detecta posibles hallazgos de incumplimiento contra Ley 21.719 (Chile), ISO/IEC 42001:2023, y/o el EU AI Act.

Este tool NO reemplaza asesoría legal. Es un motor heurístico basado en patrones de texto que apunta a los artículos/cláusulas relevantes para investigación posterior.

Args:

  • content (string): descripción del sistema en español (10-20,000 caracteres)

  • framework (opcional): 'ley_21719' | 'iso_42001' | 'eu_ai_act'. Si se omite, evalúa contra los tres frameworks.

Returns: JSON con: { "totalFindings": number, "findings": [ { "framework": string, "reference": string, "title": string, "severity": "critical"|"high"|"medium"|"low"|"info", "matchedText": string, "guidance": string } ] }

Ejemplos de uso:

  • "Audita este flujo: recolectamos huella dactilar de empleados para control de asistencia" -> detecta uso de datos biométricos

  • "Tenemos un chatbot de atención al cliente sin aviso de que es IA" -> detecta falta de transparencia (Art. 50 EU AI Act)

No usar cuando: se necesita un informe ejecutivo completo con resumen por severidad — usar gobernador_generate_compliance_report en ese caso.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYesDescripción en español del sistema, funcionalidad o flujo de datos de IA a auditar (ej. 'Chatbot que procesa datos de salud de pacientes y toma decisiones automáticas de derivación').
frameworkNoFramework normativo a evaluar: 'ley_21719' (Chile), 'iso_42001' (gestión de IA), o 'eu_ai_act' (UE). Si se omite, se evalúan los tres.
Behavior4/5

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

Annotations already declare the tool as read-only and idempotent. The description adds behavioral context by explaining it is a heuristic engine based on text patterns, does not replace legal advice, and points to relevant articles/clauses. It does not contradict annotations.

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?

The description is well-structured: purpose and disclaimer first, then parameters, return format (with JSON structure), usage examples, and finally when-not-to-use. Every sentence adds value, no fluff. It is appropriately sized for the tool's complexity.

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?

Given the tool has 2 parameters and no output schema, the description provides a complete picture: explains what the tool does, how to use it (with examples), what the output looks like (JSON schema), and when to use an alternative. All relevant context is covered.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds significant value: character limits (10-20,000), language requirement (español), explanation of the optional framework parameter with enum values, and detailed examples of usage. This goes well beyond the schema descriptions.

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 clearly states the verb ('analiza') and resource ('descripción de un sistema de IA o flujo de datos'), specifies the compliance frameworks (Ley 21.719, ISO/IEC 42001:2023, EU AI Act), and distinguishes from sibling tools by noting that for executive reports one should use gobernador_generate_compliance_report.

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?

The description explicitly states when not to use ('No usar cuando: se necesita un informe ejecutivo completo'), provides a specific alternative tool ('usar gobernador_generate_compliance_report'), and includes a disclaimer that it does not replace legal advice. This provides clear guidance on appropriate usage context.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CodexPromptusIuris/Gobernador-ia-mcp-server-'

If you have feedback or need assistance with the MCP directory API, please join our Discord server