My fix for LLM tool use issues was deleting half my tools, not writing a bigger prompt

Description and use

Removing overlapping tools and tightening schemas improved LLM agent reliability by reducing incorrect function calls.

Problem

An LLM agent kept calling the wrong function when given many overlapping tools, causing unreliable behavior.

Outcome

Reducing the number of overlapping tools and tightening their definitions led to a measurable drop in incorrect function calls and improved overall agent reliability.

Workflow

• Identify overlapping tools in the function list.
• Remove or defer tools that can answer the same request at the same time.
• Rename tools to make them mutually exclusive.
• Shorten tool descriptions to emphasize distinct use cases.
• Constrain arguments with enums and required fields, avoid large free‑form objects.
• Test agent behavior and iterate if necessary.

Evidence

The agent had access to: Slack, Notion, HubSpot, a couple of internal APIs

Source

GPT-5.4 kept calling the wrong function. Claude Opus did too, just with slightly better posture.

Source

If you give a model 15 functions that all smell like “retrieve customer info,” you have not created flexibility.

Source

I deleted half the tool list, tightened the schemas, and the agent immediately got less stupid.

Source

OpenAI’s newer Agents building blocks made this more official, but most of us learned it the annoying way in production: runtime tool selection beats front‑loading everything.

Source