Skip to main content
Glama

get_regulation_guide

Read-only

Get analysis guidance for EU regulations like GDPR, DORA, and AI Act. Discover delegated acts, proportionality tiers, common pitfalls, cross-regulation pointers, and methodology hints before analyzing regulations.

Instructions

Get analysis guidance for a specific regulation. Returns delegated acts, proportionality tiers, commonly missed provisions, cross-regulation pointers, and analysis methodology hints. Call this BEFORE analyzing any regulation to discover what data is available and how to use it effectively.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
regulationYesRegulation ID (e.g., "DORA", "GDPR", "NIS2", "AI_ACT")
detail_levelNoQuick (~500 tokens): delegated acts, proportionality, top pitfalls, cross-regulation. Full (~1500 tokens): adds key article structures, evidence hints, recitals, national law pointers. Default: quick.

Implementation Reference

  • The main handler function for the get_regulation_guide tool, which reads the appropriate JSON guide file and formats it into a string based on the requested detail level.
    export function getRegulationGuide(input: RegulationGuideInput): string {
      const { regulation, detail_level = 'quick' } = input;
      const guidePath = join(GUIDES_DIR, `${regulation}.json`);
    
      if (!existsSync(guidePath)) {
        return (
          `No analysis guide available for ${regulation}. Use list_regulations ` +
          `to discover delegated acts, check_applicability for scope, and ` +
          `compare_requirements for cross-regulation analysis.`
        );
      }
    
      const guide: GuideData = JSON.parse(readFileSync(guidePath, 'utf-8'));
      return detail_level === 'full' ? formatFullGuide(guide) : formatQuickGuide(guide);
    }
  • Input type definition for getRegulationGuide.
    export interface RegulationGuideInput {
      regulation: string;
      detail_level?: 'quick' | 'full';
    }
  • Registration of the get_regulation_guide tool in the tools registry, including its schema (though abbreviated in the summary) and its mapping to the getRegulationGuide handler.
    },
    {
      name: 'get_regulation_guide',
      description:
        'Get analysis guidance for a specific regulation. Returns delegated acts, ' +
        'proportionality tiers, commonly missed provisions, cross-regulation pointers, and ' +
        'analysis methodology hints. Call this BEFORE analyzing any regulation to discover ' +
        'what data is available and how to use it effectively.',
      inputSchema: {
        type: 'object',
        properties: {
          regulation: {
            type: 'string',
            description: 'Regulation ID (e.g., "DORA", "GDPR", "NIS2", "AI_ACT")',
          },
          detail_level: {
            type: 'string',
            enum: ['quick', 'full'],
            description:
              'Quick (~500 tokens): delegated acts, proportionality, top pitfalls, ' +
              'cross-regulation. Full (~1500 tokens): adds key article structures, evidence ' +
              'hints, recitals, national law pointers. Default: quick.',
          },
        },
        required: ['regulation'],
      },
      handler: async (_db, args) => {
        const input = args as unknown as RegulationGuideInput;
        return getRegulationGuide(input);
Behavior4/5

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

While annotations declare readOnlyHint=true, the description adds valuable behavioral context: specific token estimates (~500 vs ~1500), detailed content taxonomy of returns (cross-regulation pointers, methodology hints), and the preparatory workflow role. Does not mention caching or idempotency, but otherwise rich.

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?

Two sentences total with zero waste. First sentence front-loads the action and complete return value taxonomy. Second sentence provides imperative usage guidance. Every clause conveys unique information not duplicated in structured fields.

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?

Despite lacking an output schema, the description comprehensively enumerates return components (delegated acts, tiers, provisions, pointers, hints) that would appear in output. Combined with explicit token budgets and workflow positioning, it fully compensates for the missing output specification.

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?

With 100% schema description coverage, the schema fully documents both parameters (regulation IDs with examples, detail_level with token counts and enum descriptions). The description references 'specific regulation' but adds minimal semantic detail beyond the schema's comprehensive coverage, meeting the baseline expectation.

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 the specific verb 'Get' and resource 'analysis guidance,' then enumerates exact return components (delegated acts, proportionality tiers, etc.). It clearly distinguishes this from sibling retrieval tools like get_article by framing the output as methodological guidance rather than raw regulatory text.

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?

Explicitly states the temporal sequencing constraint: 'Call this BEFORE analyzing any regulation.' It further explains the value proposition ('discover what data is available and how to use it effectively'), providing clear guidance on when to prefer this over direct content retrieval tools.

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/Ansvar-Systems/eu-regulations'

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