Skip to main content
Glama

get_tissue_specific_genes

Identify genes with tissue-specific expression patterns using GTEx data to analyze biological functions in specific human tissues.

Instructions

Get genes with tissue-specific expression patterns

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tissueSiteDetailIdYesTissue site detail ID (e.g., Muscle_Skeletal, Brain_Cortex)
selectionCriteriaNoSelection criteria for tissue specificity (default: highestInGroup)highestInGroup
datasetIdNoGTEx dataset ID (default: gtex_v8)gtex_v8

Implementation Reference

  • The core handler function that implements the get_tissue_specific_genes tool. It fetches top expressed genes for the given tissue using the API client and formats them as tissue-specific gene candidates, including error handling and output formatting.
    async getTissueSpecificGenes(args: any) {
      if (!args.tissueId || typeof args.tissueId !== 'string') {
        throw new Error('tissueId parameter is required and must be a tissue ID string');
      }
    
      // Get top expressed genes for this tissue
      const topGenesResult = await this.apiClient.getTopExpressedGenes(
        args.tissueId,
        args.datasetId || 'gtex_v8',
        true, // Filter MT genes
        100 // Get more genes for specificity analysis
      );
    
      if (topGenesResult.error) {
        return {
          content: [{
            type: "text",
            text: `Error retrieving tissue-specific genes: ${topGenesResult.error}`
          }],
          isError: true
        };
      }
    
      const topGenes = topGenesResult.data || [];
      if (topGenes.length === 0) {
        return {
          content: [{
            type: "text",
            text: `No expression data found for tissue: ${args.tissueId}`
          }]
        };
      }
    
      // For tissue specificity, we'll analyze the top genes
      // In a real implementation, this would compare across all tissues
      const tissueDisplayName = this.getTissueDisplayName(args.tissueId);
      
      let output = `**Tissue-Specific Genes in ${tissueDisplayName}**\n`;
      output += `Dataset: ${topGenes[0]?.datasetId}\n`;
      output += `Analysis: Top expressing genes (tissue specificity analysis)\n\n`;
    
      // Show top tissue-specific candidates
      const specificGenes = topGenes.slice(0, 20);
      
      output += `**Candidate Tissue-Specific Genes (${specificGenes.length}):**\n`;
      specificGenes.forEach((gene, index) => {
        output += `${(index + 1).toString().padStart(2)}. **${gene.geneSymbol}** (${gene.gencodeId})\n`;
        output += `    • Expression: ${gene.median.toFixed(3)} ${gene.unit}\n`;
        output += `    • Rank in tissue: ${index + 1}\n`;
      });
    
      output += `\n**Note:** This analysis shows highly expressed genes in ${tissueDisplayName}. `;
      output += `True tissue specificity requires comparison across all tissues using advanced statistical methods.\n`;
    
      return {
        content: [{
          type: "text",
          text: output
        }]
      };
    }
  • The tool schema definition in the listTools response, including name, description, and inputSchema with required tissueSiteDetailId and optional parameters.
    {
      name: "get_tissue_specific_genes",
      description: "Get genes with tissue-specific expression patterns",
      inputSchema: {
        type: "object",
        properties: {
          tissueSiteDetailId: {
            type: "string",
            description: "Tissue site detail ID (e.g., Muscle_Skeletal, Brain_Cortex)"
          },
          selectionCriteria: {
            type: "string",
            description: "Selection criteria for tissue specificity (default: highestInGroup)",
            enum: ["highestInGroup", "aboveThreshold"],
            default: "highestInGroup"
          },
          datasetId: {
            type: "string",
            description: "GTEx dataset ID (default: gtex_v8)", 
            default: "gtex_v8"
          }
        },
        required: ["tissueSiteDetailId"]
      }
    },
  • src/index.ts:644-650 (registration)
    The dispatch logic in the CallToolRequestHandler that maps the tool name to the ExpressionHandlers.getTissueSpecificGenes method, passing mapped arguments.
    if (name === "get_tissue_specific_genes") {
      return await expressionHandlers.getTissueSpecificGenes({
        tissueId: args?.tissueSiteDetailId,
        selectionCriteria: args?.selectionCriteria,
        datasetId: args?.datasetId
      });
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't describe how it behaves: no information on output format, data volume, performance characteristics, error conditions, or whether it's a read-only operation (implied but not stated). This is inadequate for a tool with 3 parameters and no output schema.

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 a single, efficient sentence that states the core purpose without unnecessary words. It's appropriately sized for a tool with clear parameters documented elsewhere, though it could benefit from additional context.

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?

For a tool with 3 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what constitutes 'tissue-specific expression,' what the output looks like, or how results are formatted. Given the complexity of biological data analysis and lack of structured metadata, more context is needed for effective use.

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?

The description adds no parameter information beyond what's already in the schema (which has 100% coverage). It doesn't explain what 'tissue-specific expression patterns' means in practice, how selection criteria affect results, or provide examples of tissue IDs. The baseline score of 3 reflects adequate schema coverage but no added value from the description.

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 with a specific verb ('Get') and resource ('genes with tissue-specific expression patterns'). It distinguishes from siblings like get_gene_expression (general expression) and get_top_expressed_genes (top expressed regardless of tissue specificity), though it doesn't explicitly name these alternatives.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for tissue-specific analysis, or compare with siblings like get_gene_expression or get_top_expressed_genes that might overlap in functionality.

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/Augmented-Nature/GTEx-MCP-Server'

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