domains / families / agent-tooling / tool-design

tool-design

authentic

This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats, naming conventions, actionable error recovery messages, MCP server design, tool-set consolidation, and deciding when to add or remove an individual tool. Use this when the unit of work is a single tool or a set of tools. Route project-shape, pipeline architecture, and task-model-fit decisions to project-development; route deciding whether to introduce sub-agents to multi-agent-patterns.

When to use

• writing tool descriptions agents can route on
• designing tool schemas and response formats
• naming conventions
• actionable error recovery messages
• MCP server design
• tool-set consolidation
• deciding when to add or remove an individual tool
• debugging cases where the agent picked the wrong tool

When not to use

• project-shape decisions
• pipeline architecture decisions
• task-model-fit decisions
• deciding whether to introduce sub-agents
• reducing the token weight of tool outputs at the trajectory level

Skill page

Source