Tommy MCP server has 11 tools with basic schemas and descriptions, but significant quality gaps. All tools have descriptions (10-60 chars, mostly terse), and input schemas are present with type definitions. However, descriptions are uniformly brief and lack actionable context for LLM selection. Parameter descriptions are minimal (e.g., 'task ID to check' without format/constraints). No output schemas documented. Error handling is absent from visible code. Tool naming follows verb_noun convention (tommy_*) but lacks clarity on mutual exclusivity and dependencies (e.g., tommy_control accepts 'action' as free-form string, not enum). No evidence of pagination, rate limiting, or recovery guidance. Composition is reasonable (single responsibility per tool), but chaining requirements are undocumented.

• Add output schemas to all tools. Document return types, field names, and structure. E.g., tommy_status should return {task_id, status, output, exit_code, timestamp}.
• Convert tommy_control 'action' parameter to enum: {type: 'string', enum: ['wrap_up', 'abort', 'pivot', 'answer'], description: 'Control action to send to the task'}.
• Expand descriptions to 100-200 chars. Include WHEN to use (e.g., 'Call after tommy_dispatch to poll task progress'), prerequisites, and side effects. Reference pattern:tool-description.
• Add error handling guidance. E.g., tommy_dispatch: 'If harness not found, call tommy_list_harnesses() to see available options. If workspace path invalid, returns error with suggestion.'
• Document parameter constraints and dependencies. E.g., tommy_dispatch: 'workspace defaults to current project root; required if switching contexts. Must be absolute path or relative to project root.'