Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and error guidance. server_health has no input parameters (empty schema), dns_lookup has a well-structured schema with type and description for all three parameters. Both descriptions are present but brief (under 100 chars). No error handling guidance, no output schema documentation, no tool annotations. Naming follows verb_noun convention (good), but descriptions lack context on when to use each tool or what to expect in responses.

• Add output schema documentation to both tools. For server_health, document: {name: string, host: string, checks: {port: string, status: 'reachable' | 'failed:...'}}. For dns_lookup, document: {exit_code: int | null, stdout: string, stderr: string}.
• Convert record_type parameter to use JSON Schema enum constraint instead of prose list. This prevents LLM hallucination of invalid DNS record types.
• Expand server_health description to ~80-120 chars: 'Check TCP reachability of configured Technitium DNS servers on specified ports (default 53, 5380). Returns per-port status for each configured server. Use before dns_lookup to verify server availability.'
• Add error recovery guidance to dns_lookup description: 'If lookup fails or times out, call server_health first to verify the target server is reachable. Returns exit code, stdout, and stderr from dig command.'
• Document parameter relationships: 'server parameter must match a configured server name (e.g., 'primary'). If unsure, call server_health first to list available servers.'