What problem does it solve? Agents select and call tools based solely on descriptions, so vague names, ambiguous parameters, and unhelpful error messages cause tool-selection failures that prompt engineering cannot fix. This Skill provides principles, templates, and utilities for designing tool contracts that agents can use correctly. ## Core Features & Use Cases - Description Engineering: Structure every tool description to answer what the tool does, when to use it, what inputs it accepts, and what it returns, with concrete format examples. - Consolidation & Architectural Reduction: Apply the consolidation principle to shrink overlapping tool sets, and evaluate when primitive tools (e.g., a single bash execution tool) outperform many specialized ones, backed by a production case study showing 3.5x faster execution. - Schema Builder & Evaluator: Use the included Python utilities to build tool schemas, render markdown descriptions, score description quality across five criteria, and generate agent-recoverable error messages. - Use Case: When implementing MCP tools for a multi-server agent, apply the fully qualified ServerName:tool_name naming convention and audit descriptions with the evaluator to prevent tool-not-found and selection errors. ## Quick Start Ask the agent to design a new tool for your agent system, including its description, parameters, return format, and error handling, following the tool design guidelines.
