Three tools with complete input schemas and descriptions, but descriptions are generic and lack LLM-optimized guidance. All tools are READ_ONLY (good for safety), but descriptions don't explain WHEN to use each tool or what distinguishes them. Parameters are well-typed with enums where appropriate (artifactType in build_studio_prompt), but lack actionable constraints and dependency hints. No output schemas documented. Error handling absent.

• Expand tool descriptions to 100-150 chars. Example: 'build_source_pack: Create a structured Markdown source pack with facts, definitions, assumptions, and caveats for NotebookLM. Use this BEFORE build_studio_prompt to prepare grounded source material.'
• Document output schemas for each tool. Specify: does build_source_pack return a markdown string, a JSON object with sections, or both? Include example structure.
• Add format constraints to parameters. E.g., 'facts: array of 1-50 strings, each 10-500 chars, describing high-confidence claims from sources' instead of just 'High-confidence facts.'
• Add error handling with recovery hints. E.g., if artifactType is invalid, return 'Invalid artifactType. Valid options: source_pack, source_guide, chat_grounding, ...'
• Clarify tool selection logic in descriptions. Explain: use build_source_pack for single sources, build_artifact_prompt_pack for multi-artifact workflows, build_studio_prompt for individual artifact customization.