Server has 14 tools with basic schemas and descriptions, but significant quality gaps. All tools have descriptions (good), but most are under 100 chars and lack actionable context. Parameter descriptions are minimal or missing. No output schemas documented. All parameters marked optional=true, which violates best practices for required inputs. Error handling returns generic 'Error: {message}' without recovery guidance. No tool annotations (readOnlyHint/destructiveHint). Naming is verb-first (good), but descriptions don't explain WHEN to use each tool or dependencies between them. Example: 'get_vulnerabilty_details' (typo in name) accepts optional securityProblemId but doesn't explain what happens if omitted. 'send_slack_message' and 'create_workflow_for_problem_notification' are write operations but lack confirmation/dry-run patterns.

• Fix parameter optionality: Mark securityProblemId, problemId, entityId, dqlStatement as required (remove optional=true) in schemas. Add validation to reject empty/null values with clear error messages.
• Document output schemas for all tools. Example for list_vulnerabilities: 'Returns array of {displayId: string, securityProblemId: string, title: string, cveIds: string[]}'. This enables LLMs to chain tools correctly.
• Rename 'get_vulnerabilty_details' to 'get_vulnerability_details' (fix typo).
• Add tool annotations: mark all read-only tools with readOnlyHint=true, write tools with destructiveHint=true (send_slack_message, create_workflow_for_problem_notification, update_workflow). This helps agents reason about side effects.
• Enhance error messages with recovery guidance. Example: 'Security problem not found. Call list_vulnerabilities() first to see available IDs.' instead of generic 'Error: not found'.