Skip to main content
Glama

search_within_memory

Search for specific information within stored memory documents to retrieve relevant context for projects.

Instructions

Search for information within a memory document

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
memory_idYesThe ID of the memory document to search
queryYesThe search query (words or phrases)

Implementation Reference

  • The main handler function that executes the tool logic: validates params, reads memory, parses sections, performs case-insensitive search with scoring for phrase and term matches, formats results as Markdown, and returns structured content.
    export async function searchWithinMemoryTool(
      storageManager: StorageManager,
      args: any
    ): Promise<any> {
      const params = args as SearchWithinMemoryParams;
      
      if (!params.memory_id || !params.query) {
        throw new Error('Both memory_id and query are required');
      }
    
      // Read the memory document
      const memory = await storageManager.readMemory(params.memory_id);
      if (!memory) {
        throw new Error(`Memory document '${params.memory_id}' not found`);
      }
    
      // Parse sections for targeted search
      const sections = storageManager.parseSections(memory.content);
      
      // Prepare search query (case-insensitive)
      const query = params.query.toLowerCase();
      const queryTerms = query.split(/\s+/).filter(term => term.length > 0);
      
      interface SearchResult {
        section: string;
        matches: string[];
        score: number;
      }
      
      const results: SearchResult[] = [];
      
      // Search within each section
      sections.forEach(section => {
        const sectionContent = section.content.toLowerCase();
        const originalContent = section.content;
        
        if (sectionContent.includes(query)) {
          // Direct phrase match - highest score
          const lines = originalContent.split('\n');
          const matchingLines = lines.filter(line => 
            line.toLowerCase().includes(query)
          );
          
          results.push({
            section: section.name,
            matches: matchingLines.slice(0, 3), // Limit to 3 matches per section
            score: 10
          });
        } else {
          // Check for individual term matches
          const termMatches = queryTerms.filter(term => sectionContent.includes(term));
          
          if (termMatches.length > 0) {
            const lines = originalContent.split('\n');
            const matchingLines = lines.filter(line => {
              const lineLower = line.toLowerCase();
              return termMatches.some(term => lineLower.includes(term));
            });
            
            if (matchingLines.length > 0) {
              results.push({
                section: section.name,
                matches: matchingLines.slice(0, 2), // Fewer matches for partial matches
                score: termMatches.length
              });
            }
          }
        }
      });
      
      // Sort by score (descending) and then by section name
      results.sort((a, b) => {
        if (b.score !== a.score) {
          return b.score - a.score;
        }
        return a.section.localeCompare(b.section);
      });
      
      // Format results
      let response = `# Search Results in "${params.memory_id}"\n\n`;
      response += `**Query**: "${params.query}"\n\n`;
      
      if (results.length === 0) {
        response += `No matches found for "${params.query}".`;
      } else {
        response += `Found ${results.length} section${results.length === 1 ? '' : 's'} with matches:\n\n`;
        
        results.forEach((result, index) => {
          response += `## ${index + 1}. ${result.section}\n`;
          
          result.matches.forEach(match => {
            const trimmedMatch = match.trim();
            if (trimmedMatch) {
              // Highlight the matching terms (simple approach)
              let highlightedMatch = trimmedMatch;
              queryTerms.forEach(term => {
                const regex = new RegExp(`(${term})`, 'gi');
                highlightedMatch = highlightedMatch.replace(regex, '**$1**');
              });
              
              response += `- ${highlightedMatch}\n`;
            }
          });
          
          response += `\n`;
        });
        
        response += `---\n`;
        response += `*Search completed across ${sections.length} sections*`;
      }
    
      return {
        content: [{
          type: 'text',
          text: response
        }]
      };
    }
  • Interface defining the input parameters for the search_within_memory tool.
    export interface SearchWithinMemoryParams {
      memory_id: string;
      query: string;
    }
  • src/index.ts:123-140 (registration)
    Tool registration in ListToolsRequestSchema handler, specifying name, description, and input schema.
    {
      name: "search_within_memory",
      description: "Search for information within a memory document",
      inputSchema: {
        type: "object",
        properties: {
          memory_id: {
            type: "string",
            description: "The ID of the memory document to search",
          },
          query: {
            type: "string",
            description: "The search query (words or phrases)",
          },
        },
        required: ["memory_id", "query"],
      },
    },
  • src/index.ts:274-275 (registration)
    Dispatch logic in CallToolRequestSchema handler that invokes the tool handler.
    case "search_within_memory":
      return await searchWithinMemoryTool(storageManager, args);
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. It states the tool searches within a memory document but does not describe how the search works (e.g., keyword matching, relevance ranking), what the output looks like (e.g., snippets, full text), or any limitations (e.g., performance, access controls). For a search tool with zero annotation coverage, this leaves critical behavioral traits unspecified.

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 directly states the tool's function without unnecessary words. It is front-loaded with the core action ('Search for information') and resource ('within a memory document'), making it easy to parse. Every part of the sentence earns its place by conveying essential information succinctly.

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 a search operation, the lack of annotations, and no output schema, the description is incomplete. It does not explain what the search returns, how results are formatted, or any behavioral aspects like error handling. For a tool with two parameters and no structured output, more context is needed to understand its full functionality and limitations.

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 input schema has 100% description coverage, with clear documentation for 'memory_id' and 'query'. The description adds no additional meaning beyond what the schema provides, such as examples of queries or details on memory ID formats. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description does not compensate but also does not detract.

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

Purpose3/5

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

The description states the tool's purpose as 'Search for information within a memory document', which is clear but vague. It specifies the verb ('search') and resource ('memory document'), but does not distinguish it from siblings like 'get_full_memory' or 'get_memory_summary', which might also retrieve memory content. The purpose is understandable but lacks specificity about what type of search or information is involved.

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 does not mention prerequisites, such as needing an existing memory document, or compare it to siblings like 'get_full_memory' for broader retrieval or 'list_memories' for overviews. Without this context, users must infer usage from the tool name alone, which is insufficient for effective tool selection.

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/nmeierpolys/mcp-structured-memory'

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