Five tools with complete JSON schemas and basic descriptions, but significant gaps in parameter documentation and output schema clarity. Tool names follow verb_noun convention (resolve, find, context, contract_path, bundle) but descriptions are terse (10-50 chars, well below the 194-char baseline). No parameter descriptions visible in schemas, critical omission per pattern:tool-description. Output schemas not documented. Error handling exists but lacks recovery guidance. All tools are read-only, reducing risk but also limiting composition patterns.

• Add 50 - 150 character descriptions to every tool explaining WHAT it does, WHEN to call it, and WHAT it returns. Example: 'contextd.resolve: Discover and validate the active workspace, knowledge root, and pack configuration. Call this first to initialize context. Returns resolved paths, workspace name, and active pack list.'
• Add descriptions to every parameter. Example for 'cwd': 'Optional directory to resolve from. If omitted, uses current working directory. Must be an absolute or relative path.'
• Document output schemas for each tool. Add a 'returns' section to tool definitions specifying the structure of structuredContent. Example: 'Returns {resolved: object, knowledge_root: string, workspace: string, packs: [string], warnings: [string]}'.
• Enhance error messages with recovery guidance. When knowledge_root is not found, return: 'Could not resolve knowledge_root. Available workspaces: [list]. Try setting CONTEXTD_ROOT environment variable or passing workspace parameter.'
• Add tool annotations (readOnlyHint: true) to all five tools since they are read-only. This signals to agents that these calls are safe to retry and have no side effects.