Loading ToolBench
Gmail MCP Pack - Requires OAuth connection — gateway injects credentials via _context.gmail. Tools: list messages, get message, search, send email, list labels.
Gmail MCP Pack has clear tool names and basic schemas, but lacks critical depth in descriptions and error handling. All 5 tools have input schemas with type definitions and required fields properly declared. However, descriptions are generic (avg ~100 chars, below the 194-char baseline for A+ tools) and lack context about when to use each tool vs. alternatives. Parameter descriptions are minimal, e.g., 'Gmail search query' without explaining supported operators or constraints. No output schema documentation. Error handling is absent: gFetch() throws raw API errors without recovery guidance. The gmail_send tool lacks confirmation/dry-run pattern for an irreversible operation. No mention of rate limits, pagination limits, or field stripping for verbose API responses.
Get a specific Gmail message by ID. Returns full message details including headers, snippet, body, and labels.
List all labels in the user's Gmail account, including system labels (INBOX, SENT, TRASH, etc.) and user-created labels.
List messages in the user's Gmail inbox. Optionally filter with a search query. Returns message IDs and thread IDs.
Search Gmail messages using Gmail query syntax. Supports operators like from:, to:, subject:, has:attachment, after:, before:, is:unread, label:, etc.
Send an email from the authenticated Gmail account.
No output schema documentation. LLMs cannot plan downstream calls or extract required fields (e.g., message_id for chaining). Violates pattern:tool and mxe:include-chaining-ids.
Error handling absent. gFetch() throws raw API errors without recovery guidance. LLMs cannot self-correct or retry intelligently. Violates pattern:recovery-guide.
gmail_send lacks confirmation/dry-run pattern for irreversible operation. Agents can accidentally send emails without verification. Violates pattern:confirmation-request.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Descriptions lack context about when to use each tool vs. alternatives. gmail_list_messages vs gmail_search both search, distinction unclear. Descriptions avg ~100 chars vs 194-char baseline. Violates pattern:tool-description.
Parameter descriptions lack constraints and format guidance. 'Gmail search query' does not explain supported operators (from:, to:, has:attachment, etc.) or max_results bounds (1 - 100). Violates review:param-validation-rules.