Gmail MCP server has 11 tools with basic schemas and descriptions, but significant quality gaps. Tool names follow verb_noun convention (send_email, read_email, search_emails), which is good. However, descriptions are minimal (10-50 chars), parameter descriptions lack detail, and output schemas are not documented. No error handling guidance, no parameter constraints (enums, ranges), and no security annotations. The server exposes Gmail operations but lacks the LLM-optimization patterns needed for reliable agent use. Most tools score 35-50 individually.

• Expand all tool descriptions to 100-200 chars. Include WHAT the tool does, WHEN to use it, and what it returns. E.g., 'Send a new email to one or more recipients. Returns message ID and confirmation. Use send_email to send immediately; use draft_email to save without sending.'
• Add descriptions to all parameters. For arrays, specify element type: 'to: array of email addresses (e.g., ["[email protected]"])'. For enums, list valid values: 'messageListVisibility: one of "show", "hide"'.
• Document output schemas for all tools. E.g., read_email returns {messageId, from, to, cc, bcc, subject, body, htmlBody, timestamp, labels}. search_emails returns {messages: [{messageId, from, subject, snippet}], totalResults, nextPageToken}.
• Add error handling guidance. E.g., read_email: 'If message not found, returns error with available message IDs. Try search_emails() to find the correct message ID.'
• Standardize naming: rename createLabel → create_label, updateLabel → update_label, deleteLabel → delete_label to match snake_case convention used by other tools.