get_patent_statistics
Analyze chemical content statistics for patents to understand composition and annotations in the SureChEMBL database.
Instructions
Get statistical overview of chemical content in patents
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"document_id": "<document_id>"
},
"name": "get_patent_statistics"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| document_id | Yes | Patent document ID for statistics | |
| include_annotations | No | Include detailed annotation statistics (default: true) |
Implementation Reference
- src/index.ts:523-534 (registration)Tool registration entry in the tools list, including name, description, and input schema definition.
{ name: 'get_patent_statistics', description: 'Get statistical overview of chemical content in patents', inputSchema: { type: 'object', properties: { document_id: { type: 'string', description: 'Patent document ID for statistics' }, include_annotations: { type: 'boolean', description: 'Include detailed annotation statistics (default: true)' }, }, required: ['document_id'], }, }, - src/index.ts:576-577 (registration)Dispatch case in the CallToolRequestSchema handler that routes tool calls to the handler method.
case 'get_patent_statistics': return await this.handleGetPatentStatistics(args); - src/index.ts:1120-1229 (handler)The core handler function that implements the tool logic: validates input, fetches patent document from SureChEMBL API, parses annotations from abstracts and descriptions, computes comprehensive statistics on chemical content, and returns formatted JSON results.
private async handleGetPatentStatistics(args: any) { if (!isValidDocumentArgs(args)) { throw new McpError(ErrorCode.InvalidParams, 'Invalid document arguments'); } try { const response = await this.apiClient.get(`/document/${args.document_id}/contents`); const document = response.data.data; if (!document) { throw new Error('Document not found'); } const includeAnnotations = args.include_annotations !== false; // Extract basic document information const docInfo = document.contents?.patentDocument?.bibliographicData; const abstracts = document.contents?.patentDocument?.abstracts || []; const descriptions = document.contents?.patentDocument?.descriptions || []; // Collect all chemical annotations const allAnnotations: any[] = []; abstracts.forEach((abstract: any) => { if (abstract.section?.annotations) { abstract.section.annotations.forEach((annotation: any) => { allAnnotations.push({ ...annotation, source: 'abstract', language: abstract.lang }); }); } }); descriptions.forEach((description: any) => { if (description.section?.annotations) { description.section.annotations.forEach((annotation: any) => { allAnnotations.push({ ...annotation, source: 'description', language: description.lang }); }); } }); // Calculate statistics const chemicalAnnotations = allAnnotations.filter(a => a.category === 'chemical'); const uniqueChemicals = [...new Set(chemicalAnnotations.map(a => a.name))]; const chemicalFrequencies = chemicalAnnotations.reduce((acc: any, annotation: any) => { acc[annotation.name] = (acc[annotation.name] || 0) + 1; return acc; }, {}); const statistics = { document_id: args.document_id, document_info: { title: docInfo?.inventionTitles?.find((t: any) => t.lang === 'EN')?.title || 'N/A', publication_number: docInfo?.publicationReference?.[0]?.ucid || 'N/A', publication_date: docInfo?.publicationReference?.[0]?.documentId?.[0]?.date || 'N/A' }, content_statistics: { total_sections: abstracts.length + descriptions.length, abstract_sections: abstracts.length, description_sections: descriptions.length, languages: [...new Set([...abstracts, ...descriptions].map((s: any) => s.lang))] }, chemical_statistics: { total_chemical_annotations: chemicalAnnotations.length, unique_chemicals_count: uniqueChemicals.length, most_frequent_chemicals: Object.entries(chemicalFrequencies) .sort(([,a], [,b]) => (b as number) - (a as number)) .slice(0, 10) .map(([name, count]) => ({ name, count })), annotation_sources: { abstract: chemicalAnnotations.filter(a => a.source === 'abstract').length, description: chemicalAnnotations.filter(a => a.source === 'description').length } }, annotation_categories: { chemical: chemicalAnnotations.length, other: allAnnotations.length - chemicalAnnotations.length, total: allAnnotations.length } }; if (includeAnnotations) { (statistics as any).detailed_annotations = { chemical_annotations: chemicalAnnotations, unique_chemicals: uniqueChemicals, chemical_frequencies: chemicalFrequencies }; } return { content: [ { type: 'text', text: JSON.stringify(statistics, null, 2), }, ], }; } catch (error) { throw new McpError( ErrorCode.InternalError, `Failed to get patent statistics: ${error instanceof Error ? error.message : 'Unknown error'}` ); } } - src/index.ts:104-114 (schema)Type guard function for validating input arguments matching the tool's input schema (document_id required, include_annotations optional). Used in the handler.
const isValidDocumentArgs = ( args: any ): args is { document_id: string; include_annotations?: boolean } => { return ( typeof args === 'object' && args !== null && typeof args.document_id === 'string' && args.document_id.length > 0 && (args.include_annotations === undefined || typeof args.include_annotations === 'boolean') ); };