Engineering

MCP Tools and Resources: Designing Useful AI Capabilities

How to think about splitting read resources and action tools so AI agents stay accurate and safe.

May 30, 2026 5 min read MCP360 Team

TL;DR

Use resources for stable read context (account lists, schemas, cached reports) and tools for actions and fresh queries. Granular tools reduce hallucinated parameters and make audit logs meaningful.

Poorly designed tool catalogs confuse models and operators alike. The Model Context Protocol gives you two primitives — tools and resources — and using each correctly improves reliability.

Resources: Ground Truth Without Side Effects

Resources should expose data the model needs repeatedly: connected account IDs, currency settings, field definitions, or yesterday's cached performance summary. Fetching a resource never mutates vendor state.

Example: before analyzing campaigns, the model reads a resource describing available ad accounts and their time zones. That prevents off-by-one date errors in reports.

Tools: Verbs With Clear Scope

Each tool should do one job with explicit parameters:

  • `list_campaigns` — pagination, date range, status filters
  • `get_campaign_metrics` — campaign ID, metrics array, granularity
  • `update_daily_budget` — campaign ID, new budget, currency
  • Avoid mega-tools like manage_campaigns with opaque action enums. Smaller surfaces map cleanly to user intent and log entries.

    Descriptions Matter

    The model chooses tools from natural-language descriptions. Include constraints in the description: "Requires campaign_id from list_campaigns. Cannot exceed org budget safety limits."

    MCP360 maintains 50–100+ tools per service with consistent naming prefixes (meta_, google_) so multi-platform prompts disambiguate correctly on Ad Platform MCP.

    Read-Only Keys for Exploration

    Issue read-only API keys while operators learn phrasing. Graduate to write tools after validating metrics match native ad UIs. See Claude Desktop setup for a safe first connection.

    Further Reading

  • [MCP protocol explained](/blog/mcp-protocol-explained) — transports and discovery
  • [MCP vs function calling](/blog/mcp-vs-function-calling) — portability trade-offs
  • About the author

    MCP360 TeamTechnical writers covering MCP standards, hosting, and production deployment patterns.

    Ready to try MCP360?

    Connect your business tools to Claude, ChatGPT, or any AI agent. Free plan available.

    Read the glossary

    Related in this cluster