PromptForge has 4 tools with basic naming (verb_noun pattern) and descriptions present. However, parameter descriptions are minimal or absent, schemas lack detail, and error handling is weak. forge_run accepts an untyped 'params' object with no validation guidance. Output schemas are undocumented. No tool annotations (readOnlyHint, etc.). Descriptions are adequate (100-150 chars) but lack actionable context for LLM selection. This is a typical community server with functional but incomplete definitions.

• Add explicit output schema documentation to each tool. E.g., forge_list should document: returns array of {name: string, version: string, description: string, tags: string[], author: string}. Include pagination if results can exceed 50 items.
• Replace forge_run's untyped 'params' object with a structured schema. Either: (1) accept a JSON string with validation inside, or (2) dynamically generate a schema based on the package's schema.json and expose it via forge_info, then document that forge_run accepts the same structure.
• Add tool annotations to all tools. Use readOnlyHint: true for all four (they do not modify state). This signals to LLMs that these are safe to call speculatively.
• Enhance error messages with recovery guidance. E.g., forge_run validation failure should return: 'Invalid params for package "X": missing required field "Y". Call forge_info("X") to see the full schema.' instead of just listing missing fields.
• Expand parameter descriptions. E.g., forge_search: 'Search keyword (1-100 chars, searches package name, description, and tags). Returns up to 20 matches sorted by relevance.'