Articles Videos Courses Services

Language

Loading

AI Expert OÜ

Learn AI. Grow with AI.

Articles Videos Services For Companies About Contact Us

© 2026 AI Expert OÜ. All rights reserved. · Registry code: 17268273 · Contact Us

Building more effective AI agents — AI Expert OÜ

Building more effective AI agents

19 minutesAdvancedAI for BusinessConcept still relevantReviewed May 18, 2026

Anthropic. Anthropic engineers walking through what they actually changed when their multi-agent systems were misusing tools — collapsing endpoints, returning names instead of IDs, leaning on MCPs and Agent Skills instead of stuffing more tools into the system prompt. Maps point-for-point onto the article's checklist for tool descriptions and return-shape design.

AI Expert note

The examples are Anthropic-specific, but the design lesson is stable: reduce tool ambiguity, return useful identifiers and test tool choice on real tasks. Re-check current Agent Skills and MCP guidance before copying any product-specific pattern.

What you should get from this

Improve tool design so agents select the right action with the right parameters.

Watch or know first

Know the difference between a tool schema, tool description and agent instruction.

Practical next step

Watch with the companion article open, then write down one workflow or decision this changes for your own work.

Watch next

Continue through the same learning path with the next curated companion videos.

Further reading

Most MCP tools we see are technically correct and practically useless. LLMs ignore them, misuse them, or call them in unhelpful ways. The principles for designing tools LLMs adopt naturally, with examples of common failures and their fixes.

Related videos

Building Production-Ready RAG Applications: Jerry Liu

Identify the production RAG controls missing from naive document-chat demos.

Graph RAG: Improving RAG with Knowledge Graphs

Understand the Microsoft-style GraphRAG flow: entity extraction, communities, summaries and query-focused synthesis.

Developing an LLM: Building, Training, Finetuning

Sebastian Raschka's slower walkthrough of where fine-tuning sits in the broader LLM training pipeline — instruction tuning, classification fine-tuning, parameter-efficient methods, and the trade-offs the article calls.

Designing MCP tools that LLMs actually use correctly

Read the article

From Hype to Habit: How Tech Companies Are Scaling AI Beyond the Experimental

Private AI vs. Cloud: How Enterprise Leaders Can Make Smarter Build-or-Buy Decisions

AI Code Generation: Wins, Fails and the Future

Vertical AI Agents Could Be 10X Bigger Than SaaS