Habilidades agent-tool-builder
📦

agent-tool-builder

Seguro

Build reliable agent tool schemas

Poorly designed tool schemas cause agents to hallucinate, fail silently, or waste tokens. This skill teaches proven patterns for clear, unambiguous function-calling interfaces that work reliably.

Soporta: Claude Codex Code(CC)
🥉 74 Bronce
1

Descargar el ZIP de la skill

2

Subir en Claude

Ve a Configuración → Capacidades → Skills → Subir skill

3

Activa y empieza a usar

Pruébalo

Usando "agent-tool-builder". A tool that searches a database with vague description: 'Searches for things'

Resultado esperado:

Improved: 'Searches the products database by category, price range, or keyword. Returns matching product records with id, name, price, and availability. Use when users ask about specific products or browse categories.'

Usando "agent-tool-builder". Tool that fails silently on invalid input

Resultado esperado:

Enhanced error handling: Returns structured error with 'error_type': 'invalid_parameter', 'field': 'price_max', 'message': 'Value must be positive number', 'suggestion': 'Check user input and retry with valid price'

Auditoría de seguridad

Seguro
v1 • 2/24/2026

This skill is purely documentation providing guidance on agent tool design. Static analyzer flagged false positives: line 54 contains skill names (not shell commands), and cryptographic warnings matched keywords in prose (no actual code present). No executable code exists in this markdown file - it is instructional content only.

1
Archivos escaneados
58
Líneas analizadas
0
hallazgos
1
Auditorías totales
No se encontraron problemas de seguridad
Auditado por: claude

Puntuación de calidad

38
Arquitectura
100
Mantenibilidad
87
Contenido
50
Comunidad
100
Seguridad
91
Cumplimiento de la especificación

Lo que puedes crear

Build Custom Agent Tools

Design tool schemas for domain-specific operations like database queries, API integrations, or file operations that your agent needs to perform.

Improve Existing Function Calling

Refine poorly performing tools that cause hallucinations or inconsistent behavior by applying clear schema design principles.

Implement MCP Tool Integration

Create Model Context Protocol compliant tools that enable agents to interact with external systems safely and predictably.

Prueba estos prompts

Basic Tool Schema Review 
Review this tool schema and identify ambiguous descriptions or parameters that could cause inconsistent LLM behavior: [paste your schema]
Error Response Design 
Design error response formats for a [tool name] that help the LLM understand what went wrong and how to recover or retry with corrected parameters.
Tool Description Optimization 
Rewrite this tool description to be more specific about what the tool does, when to use it, and what outputs to expect: [paste current description]
Complete Tool Set Design 
I need an agent to [describe goal]. Design a minimal set of 3-5 tools with clear schemas, descriptions, and example inputs that accomplish this without overlap or ambiguity.

Mejores prácticas

  • Write descriptions that specify exactly when to use the tool and what it returns
  • Include concrete input examples showing typical parameter values
  • Design error responses that help the LLM understand and recover from failures
  • Limit tool sets to the minimum needed - too many options cause confusion
  • Use specific parameter names and types that match the domain vocabulary

Evitar

  • Vague descriptions like 'processes data' or 'handles requests' without specifics
  • Silent failures that return empty results instead of explicit error messages
  • Providing 20+ tools when 5-7 focused tools would be more effective
  • Schemas that accept any value without validation constraints
  • Descriptions that explain implementation instead of purpose and behavior

Preguntas frecuentes

How many tools should I provide to an agent?
Start with 5-7 focused tools. More than 10 often causes decision paralysis and increases token costs. Add tools only when existing ones cannot accomplish required tasks.
What makes a tool description effective?
Effective descriptions state: what the tool does, when to use it, what parameters it expects, and what output format it returns. Avoid explaining implementation details.
How do I handle tool errors gracefully?
Return structured errors with an error type, the specific field that failed, a human-readable message, and a suggestion for how to fix and retry the operation.
Should I provide examples for every tool parameter?
Provide at least one complete example showing typical parameter values. For complex parameters or unusual formats, add specific examples for those fields.
What is MCP and should I use it?
MCP (Model Context Protocol) is a standard for connecting AI models to tools and data sources. Use it when building tools that need to work across different AI platforms or with external systems.
How do I test if my tool schemas work well?
Test with varied natural language prompts that should trigger the tool. Verify the LLM correctly identifies when to use it, provides valid parameters, and handles errors appropriately.

Detalles del desarrollador

Autor

sickn33

Licencia

MIT

Repositorio

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/agent-tool-builder

Ref.

main

Estructura de archivos

📄 SKILL.md