Skip to main content
Glama
taehojo
by taehojo

analyze_gwas_locus

Analyze GWAS locus variants to rank them by regulatory impact for fine-mapping and causal variant identification.

Instructions

Analyze all variants in a GWAS locus.

Ranks variants by regulatory impact for fine-mapping and causal variant identification.

Perfect for: GWAS follow-up, fine-mapping, identifying causal variants.

Example: "Analyze GWAS locus with 10 variants"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
variantsYes
chromosomeNo
startNo
endNo

Implementation Reference

  • MCP CallTool request handler case for 'analyze_gwas_locus': validates input (implicitly via schema), calls AlphaGenomeClient.analyzeGwasLocus, and returns JSON-formatted result.
    case 'analyze_gwas_locus': {
      const result = await getClient().analyzeGwasLocus(args);
      return {
        content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
      };
    }
  • Tool schema and definition: specifies name, description, input schema with variants array (required), optional chromosome/start/end for locus.
    export const ANALYZE_GWAS_LOCUS_TOOL: Tool = {
      name: 'analyze_gwas_locus',
      description: `Analyze all variants in a GWAS locus.
    
    Ranks variants by regulatory impact for fine-mapping and causal variant identification.
    
    Perfect for: GWAS follow-up, fine-mapping, identifying causal variants.
    
    Example: "Analyze GWAS locus with 10 variants"`,
      inputSchema: {
        type: 'object',
        properties: {
          variants: {
            type: 'array',
            items: {
              type: 'object',
              properties: {
                chromosome: { type: 'string' },
                position: { type: 'number' },
                ref: { type: 'string' },
                alt: { type: 'string' },
              },
              required: ['chromosome', 'position', 'ref', 'alt'],
            },
            minItems: 1,
          },
          chromosome: { type: 'string' },
          start: { type: 'number' },
          end: { type: 'number' },
        },
        required: ['variants'],
      },
    };
  • src/index.ts:99-101 (registration)
    MCP ListTools request handler that registers and exposes all tools, including analyze_gwas_locus via ALL_TOOLS import.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return { tools: ALL_TOOLS };
    });
  • src/tools.ts:709-730 (registration)
    Central registration array ALL_TOOLS that includes ANALYZE_GWAS_LOCUS_TOOL for exposure via MCP ListTools.
    export const ALL_TOOLS: Tool[] = [
      PREDICT_VARIANT_TOOL,
      BATCH_SCORE_TOOL,
      ASSESS_PATHOGENICITY_TOOL,
      PREDICT_TISSUE_SPECIFIC_TOOL,
      COMPARE_VARIANTS_TOOL,
      PREDICT_SPLICE_IMPACT_TOOL,
      PREDICT_EXPRESSION_IMPACT_TOOL,
      ANALYZE_GWAS_LOCUS_TOOL,
      COMPARE_ALLELES_TOOL,
      BATCH_TISSUE_COMPARISON_TOOL,
      PREDICT_TF_BINDING_IMPACT_TOOL,
      PREDICT_CHROMATIN_IMPACT_TOOL,
      COMPARE_PROTECTIVE_RISK_TOOL,
      BATCH_PATHOGENICITY_FILTER_TOOL,
      COMPARE_VARIANTS_SAME_GENE_TOOL,
      PREDICT_ALLELE_SPECIFIC_EFFECTS_TOOL,
      ANNOTATE_REGULATORY_CONTEXT_TOOL,
      BATCH_MODALITY_SCREEN_TOOL,
      GENERATE_VARIANT_REPORT_TOOL,
      EXPLAIN_VARIANT_IMPACT_TOOL,
    ];
  • AlphaGenomeClient helper method that bridges to Python subprocess for 'analyze_gwas_locus' action.
    async analyzeGwasLocus(params: any): Promise<any> {
      try {
        return await this.callPythonBridge('analyze_gwas_locus', params);
      } catch (error) {
        if (error instanceof ApiError) throw error;
        throw new ApiError(`GWAS locus analysis failed: ${error}`, 500);
      }
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the tool 'ranks variants by regulatory impact,' it doesn't describe what the ranking criteria are, what format the output takes, whether this is a computationally intensive operation, what happens with invalid inputs, or any rate limits. For a tool with 4 parameters and no output schema, this leaves significant behavioral gaps.

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 description is appropriately concise with four sentences that each add value: stating the core function, explaining the ranking purpose, providing usage context, and giving an example. It's front-loaded with the main purpose and wastes no words. The structure could be slightly improved by integrating the example more naturally, but overall it's efficient.

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

Completeness2/5

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

Given the complexity of GWAS analysis, 4 parameters with 0% schema coverage, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what the tool returns, how the ranking works, what regulatory impact means in this context, or how the parameters interact. For a tool that presumably returns ranked variants with impact scores, the lack of output information is a significant gap.

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

Parameters2/5

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

With 0% schema description coverage for 4 parameters, the description provides no information about what the parameters mean or how they should be used. The description mentions 'variants' and 'GWAS locus' but doesn't explain the relationship between the 'variants' array parameter and the 'chromosome', 'start', and 'end' parameters. The example is too vague to provide parameter guidance.

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

Purpose4/5

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

The description clearly states the tool's purpose: analyzing variants in a GWAS locus to rank them by regulatory impact for fine-mapping and causal variant identification. It specifies the verb 'analyze' and resource 'GWAS locus variants', making it distinct from many sibling tools that focus on prediction, comparison, or annotation rather than comprehensive locus analysis. However, it doesn't explicitly differentiate from all siblings like 'batch_score_variants' or 'explain_variant_impact' which might have overlapping functionality.

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?

The description provides clear usage context with 'Perfect for: GWAS follow-up, fine-mapping, identifying causal variants' and includes an example. This gives good guidance about when to use this tool. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the sibling tools, which would be needed for a perfect score.

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/taehojo/alphagenome-mcp'

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