Kennelbox provides 5 tools with basic schemas and descriptions, but falls short of production quality. Tool names are clear (read_file, write_file, edit_file, list_directory, run_command), but descriptions are minimal (10-50 chars, well below the 194-char baseline). Parameter descriptions exist but lack detail on constraints, formats, and error recovery. No output schemas documented. Critical security concerns: run_command accepts arbitrary shell commands with only an allowlist guard (not visible in provided code), and write_file/edit_file lack confirmation patterns for destructive operations. Error handling is absent, no guidance on recovery, retryability, or actionable error messages. The tool set is narrow and composition-focused on file/command operations, but lacks pagination, batch operations, and idempotent guarantees.
Edit a file by replacing old_string with new_string
List contents of a directory within the project
Read the contents of a file within the project
Run a shell command within the sandboxed environment
Write content to a file within the project
Descriptions are critically short (10-50 chars vs 194-char baseline). 'Write content to a file' and 'Edit a file by replacing old_string with new_string' lack context on when to use, prerequisites, and side effects. LLMs cannot reliably select between write_file and edit_file without richer guidance.
No output schemas documented. Callers do not know what fields read_file, list_directory, or run_command return. This forces LLMs to guess at response structure and breaks downstream tool chaining.
Destructive operations (write_file, edit_file, run_command) lack confirmation or dry-run patterns. Agents can overwrite files or execute arbitrary commands without a safety gate. No error recovery guidance provided.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 46 | 2026-07-28+ | v2 |
Parameter descriptions lack constraint details. 'path' is described as 'Relative path from project root' but does not specify: allowed characters, max length, symlink handling, or path traversal prevention. 'command' in run_command has no format guidance or examples of valid allowlisted commands.
No error handling or recovery guidance. Tools do not document what errors are retryable, user-fixable, or fatal. No actionable error messages shown (e.g., 'File not found. Check path with list_directory()' vs bare 404).