Loading ToolBench
Email MCP server with support for IMAP, SMTP, and common email operations
Email MCP server has 4 tools with basic schemas and descriptions, but significant gaps in parameter documentation, output schema clarity, and error handling. Tool names follow verb_noun convention (list_, create_, delete_) which is good. However, descriptions are minimal (10-50 chars), parameter descriptions are sparse or missing, and output schemas are not documented. No error recovery guidance, no input validation hints, and no security annotations visible. The server uses file-based logging and environment variable injection for credentials (good), but lacks tool-level permission gates and audit trail documentation.
Create a new mailbox/folder.
Delete a mailbox/folder.
List all mailboxes/folders in the email account.
List messages in a folder with optional limit.
Descriptions are too short (10-50 chars). Rubric baseline is 194 chars avg; descriptions under 20 chars score 0-20. Current descriptions lack WHEN to use, WHAT it returns, and prerequisites.
Output schemas are not documented. LLMs cannot plan downstream calls or extract required fields (e.g., mailbox IDs for chaining). Rubric requires documented return types for all tools.
No error handling guidance. Tools lack recovery hints (e.g., 'If authentication fails, check EMAIL_USER and EMAIL_PASSWORD env vars'). Errors should guide LLM on retry vs. user-fixable vs. fatal.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | <=2025-11-25 | v2 |
Destructive tools (delete_mailbox) lack confirmation/dry-run pattern. Agents can permanently delete mailboxes without safeguards. No idempotent or confirmation hints visible.
Parameter 'folder' in list_messages lacks enum or validation hints. Should document expected format (e.g., 'INBOX', 'Sent', or custom folder names) to prevent hallucinated values.