# SKILL: MCP Tool Selection Agent Skill

## Purpose
Choose the right MCP/tool integration for an agent task while avoiding unnecessary permissions and tool sprawl.

## When to Use
Use this when the user needs to: Choose the right MCP/tool integration for an agent task while avoiding unnecessary permissions and tool sprawl. It is designed for repeatable agent or automation work, not one-off fluffy prompting.

## Inputs Required
- Agent goal
- Candidate tools
- Data needed
- Allowed permissions
- Deployment environment

## Workflow
1. Define the minimum tool capability required
2. Compare candidate tools against permission needs
3. Reject tools that expose unrelated sensitive data
4. Define logging and approval requirements
5. Recommend the smallest viable integration

## Output Format
Tool-selection matrix with recommendation, permission notes, and deployment checklist.

## Quality Rules
- Ground every claim in supplied inputs or clearly mark it as an assumption.
- Prefer specific fields, examples, and decision points over generic advice.
- Include a test command and pass criteria so the skill can be evaluated.
- Keep the output usable by a human first and automation-ready second.

## Guardrails
- Do not send emails, publish posts, contact leads, change calendars, spend money, delete data, or alter production systems without explicit human approval.
- Do not invent facts, private details, legal claims, prices, or external data.
- For web or profile research, use current sources and separate evidence from inference.
- For connected tools, use the minimum permission needed and log the action taken.

## Test Command
Run this skill on a simple example for MCP Tool Selection Agent Skill and return the expected output structure plus any missing inputs.