Single tool 'promptpack_scan' has a basic description but critically lacks parameter descriptions and output schema documentation. The input schema defines 'target' as a string but provides no guidance on expected format, valid paths, or constraints. No error handling guidance. Tool name is acceptable (verb_noun pattern) but the overall definition is incomplete for LLM-driven agent use.

• Add parameter description for 'target': 'Absolute or relative filesystem path to scan for code markers (TODO, FIXME, XXX). Supports directories and files. Required.'
• Document output schema: 'Returns {"tool": string, "findings": [{"id": string, "sev": string, "where": string}], "score": number}. Findings are sorted by severity (high, medium, low).'
• Expand tool description to 100 - 150 chars: 'Scans a directory or file for code markers (TODO, FIXME, XXX) and returns findings with severity levels. Use this to audit prompt templates for incomplete or flagged sections before deployment.'
• Add error handling: 'If target does not exist, returns error with message "Path not found: {path}". If target is not readable, returns "Permission denied: {path}". Both are user-fixable.'
• Migrate from STDIO to HTTP+SSE or Streamable HTTP transport to enable remote client access and hosted deployment.