Skip to main content
Glama

search_files

Search your notes directory recursively for files and directories matching a pattern, including partial names. Exclude specific items using glob patterns to find notes even when their exact location is unknown.

Instructions

Recursively search for files and directories matching a pattern in your notes directory. The search is case-insensitive and matches partial names. Returns full paths to all matching items. Great for finding notes when you don't know their exact location.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
excludePatternsNoGlob patterns to exclude from search results
patternYesThe pattern to search for in file and directory names

Implementation Reference

  • Registration and dispatch for the "search_files" tool in the main handleToolCall switch statement, calling the dedicated handleSearchFiles function.
    case "search_files":
      return await handleSearchFiles(notesPath, args);
  • Supporting utility that performs recursive file search matching a pattern in filenames, with exclusion patterns. This is the core search logic powering the search_files tool.
    export async function searchFiles(rootPath: string, pattern: string, excludePatterns: string[] = []): Promise<string[]> {
      const results: string[] = [];
      
      // Normalize the search pattern for better matching
      const normalizedPattern = pattern.toLowerCase();
    
      // Make sure the root path exists
      try {
        const rootStats = await fs.stat(rootPath);
        if (!rootStats.isDirectory()) {
          console.error(`Search root is not a directory: ${rootPath}`);
          return [];
        }
      } catch (error) {
        console.error(`Error accessing search root path ${rootPath}:`, error);
        return [];
      }
    
      async function search(currentPath: string): Promise<void> {
        try {
          // Read directory entries
          const entries = await fs.readdir(currentPath, { withFileTypes: true });
    
          for (const entry of entries) {
            const fullPath = path.join(currentPath, entry.name);
            
            try {
              // Check if path matches any exclude pattern
              const relativePath = path.relative(rootPath, fullPath);
              const shouldExclude = excludePatterns.some(pattern => {
                const globPattern = pattern.includes('*') ? pattern : `**/${pattern}/**`;
                return minimatch(relativePath, globPattern, { dot: true });
              });
    
              if (shouldExclude) {
                continue;
              }
    
              // Match the name (case-insensitive)
              if (entry.name.toLowerCase().includes(normalizedPattern)) {
                results.push(fullPath);
              }
    
              // Recursively search subdirectories
              if (entry.isDirectory()) {
                await search(fullPath);
              }
            } catch (error) {
              // Skip problematic entries
              console.error(`Error processing ${fullPath}:`, error);
              continue;
            }
          }
        } catch (error) {
          console.error(`Error reading directory ${currentPath}:`, error);
        }
      }
    
      // Start the search
      await search(rootPath);
      
      // Log the number of results found
      console.error(`Search found ${results.length} results for pattern "${pattern}" in ${rootPath}`);
      
      return results;
    }
Behavior4/5

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

With no annotations provided, the description carries the full burden and does well by disclosing key behavioral traits: it's a read-only search (implied by 'search'), recursive, case-insensitive, matches partial names, and returns full paths. It doesn't mention rate limits, permissions, or error handling, but covers the core operation adequately for a search tool.

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 appropriately sized and front-loaded: the first sentence covers the core functionality, the second adds behavioral details, and the third provides usage context. Every sentence earns its place with no wasted words, making it efficient and easy to scan.

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

Completeness4/5

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

Given the tool's moderate complexity (search with two parameters), no annotations, and no output schema, the description is fairly complete: it explains what the tool does, how it behaves, and when to use it. It lacks details on output format beyond 'full paths' (e.g., structure or pagination) and doesn't cover edge cases, but it's sufficient for basic 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?

Schema description coverage is 100%, so the schema already documents both parameters (pattern and excludePatterns). The description adds some context by mentioning 'pattern' is matched in names and search is 'case-insensitive' and 'partial', but doesn't provide additional syntax or format details beyond what the schema implies. Baseline 3 is appropriate as the schema does the heavy lifting.

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 clearly states the tool's purpose with specific verbs ('recursively search for files and directories') and resources ('in your notes directory'), distinguishing it from siblings like list_directory (which lists without searching) or read_note (which reads specific files). It explicitly mentions what it returns ('full paths to all matching items').

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 context for when to use this tool ('Great for finding notes when you don't know their exact location'), which implicitly differentiates it from tools like read_note (for known files) or list_directory (for browsing). However, it doesn't explicitly state when not to use it or name alternatives like evaluateInsight or rollup, which might serve different search purposes.

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

Related 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/markacianfrani/mcp-notes'

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