Tidebreak defines 4 tools with basic schemas and descriptions, but falls short of production quality. All tools have descriptions (10-60 chars, below the 50-200 char baseline for LLM optimization) and input schemas with typed parameters. However, descriptions lack actionable context, they state WHAT but not WHEN or WHY. The exec tool is particularly risky: no error guidance, no dry-run pattern, no permission checks documented. Parameters lack constraints (enums, ranges, format hints). Output schemas are not documented. No recovery guidance for failures. Naming is verb-first (good), but descriptions are too terse to guide LLM selection or parameter usage.

• Expand tool descriptions to 80-150 chars. Include WHEN to use (e.g., 'Call read_file to retrieve file contents when you need to inspect code, config, or logs. Use list_dir first to discover available files.')
• Add output schema documentation for each tool. E.g., read_file returns {content: string, size_bytes: number, encoding: string}; list_dir returns {entries: [{name, type, size}], total_count}.
• For exec, add a dry-run parameter (boolean, default false) and document: 'Set dry_run=true to preview the command without executing. Irreversible operations require explicit confirmation.'
• Add parameter constraints: path should validate against path traversal (no '../'); command should restrict to a whitelist or document sandbox limits; args should have max length.
• Document error recovery for each tool. E.g., 'If read_file returns permission_denied, check file ownership. If exec times out, the command may be hung, consider a shorter timeout or simpler command.'