Skip to main content
Glama
cexll
by cexll

fetch-chunk

Retrieves cached data chunks from partial responses in the Codex MCP Server, enabling sequential access to large code analysis results for AI-assisted programming tasks.

Instructions

Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cacheKeyYesThe cache key provided in the initial changeMode response
chunkIndexYesWhich chunk to retrieve (1-based index)

Implementation Reference

  • The main execute function that handles the tool invocation: parses args, fetches chunks from cache using getChunks, validates chunkIndex, formats the response with formatChangeModeResponse, adds summary if first chunk, and returns formatted output or error messages.
      execute: async (args: any, onProgress?: (newOutput: string) => void): Promise<string> => {
        const { cacheKey, chunkIndex } = args;
    
        Logger.toolInvocation('fetch-chunk', args);
        Logger.debug(`Fetching chunk ${chunkIndex} with cache key: ${cacheKey}`);
    
        // Retrieve cached chunks
        const chunks = getChunks(cacheKey);
    
        if (!chunks) {
          return `❌ Cache miss: No chunks found for cache key "${cacheKey}". 
    
      Possible reasons:
      1. The cache key is incorrect. Did you run ask-codex with changeMode enabled?
      2. The cache has expired (10 minute TTL)
      3. The MCP server was restarted and the file-based cache was cleared
    
    Please re-run the original changeMode request to regenerate the chunks.`;
        }
    
        // Validate chunk index
        if (chunkIndex < 1 || chunkIndex > chunks.length) {
          return `❌ Invalid chunk index: ${chunkIndex}
    
    Available chunks: 1 to ${chunks.length}
    You requested: ${chunkIndex}
    
    Please use a valid chunk index.`;
        }
    
        // Get the requested chunk
        const chunk = chunks[chunkIndex - 1];
    
        // Format the response
        let result = formatChangeModeResponse(chunk.edits, {
          current: chunkIndex,
          total: chunks.length,
          cacheKey,
        });
    
        // Add summary for first chunk
        if (chunkIndex === 1 && chunks.length > 1) {
          const allEdits = chunks.flatMap(c => c.edits);
          result = summarizeChangeModeEdits(allEdits, true) + '\n\n' + result;
        }
    
        Logger.debug(
          `Returning chunk ${chunkIndex} of ${chunks.length} with ${chunk.edits.length} edits`
        );
    
        return result;
      },
  • Zod input schema defining the required parameters: cacheKey (string) and chunkIndex (number >=1).
    const inputSchema = z.object({
      cacheKey: z.string().describe('The cache key provided in the initial changeMode response'),
      chunkIndex: z.number().min(1).describe('Which chunk to retrieve (1-based index)'),
    });
  • The fetchChunkTool is imported (line 8) and registered by pushing it to the toolRegistry array alongside other tools.
    toolRegistry.push(
      askCodexTool,
      batchCodexTool,
      // reviewCodexTool,
      pingTool,
      helpTool,
      versionTool,
      brainstormTool,
      fetchChunkTool,
      timeoutTestTool
    );

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations provided, the description carries the behavioral burden. The word 'Retrieves' signals a read operation, and 'cached chunks' implies a non-destructive lookup from previously stored response data. It does not detail cache expiration or whether chunks can be re-fetched, but the core behavior is clear.

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?

Two short sentences deliver the core behavior and the intended usage context with no wasted words. The primary action is front-loaded and the follow-up guidance is immediately actionable.

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?

The description gives enough context for a simple two-parameter fetch tool: where the cacheKey comes from and when to call it. With no output schema, it could have clarified the response shape or chunk count, but the invocation path is adequately complete.

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 parameters are already well documented. The description adds context about when the cacheKey/chunkIndex are used, but it does not provide substantial extra meaning beyond the schema.

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 states a specific verb and resource: it retrieves cached chunks from a changeMode response. It also clarifies the tool's role as the follow-up mechanism for partial changeMode responses, making its purpose unmistakable.

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 explicitly says to use this tool 'after receiving a partial changeMode response' and positions it as the way to get subsequent chunks. It does not mention exclusions or alternatives, but no directly competing sibling tool is apparent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.