Reducing Tool Calls in Agentic AI

A developer experimenting with local-LLM agentic AI workflows found that combining tool calls—such as having a single `read_blog_post` MCP tool internally perform `find_blog_date`—reduces the number of tool calls from two to one, improving performance, reducing GPU usage, and increasing user satisfaction. The optimization was tested with Gemma 4 E4B as the LLM.

I have been experimenting with optimizing my local-LLM agentic AI workflow. Currently I have Gemma 4 E4B other models work well too, but this one seems reliable and fast as the LLM. In testing my system, I found that a simple query, like "summarize the Kimi-K3 blog post" was slower than necessary because the agent had to call multiple tools to resolve the query. It had to find the date with find blog date or similar and then read blog post . I decided to try to reduce and combine tool calls —the read blog post MCP tool call could internally perform find blog date . The instructions on the tools would be updated to note the new calling pattern. So I could resolve a query with 1 tool call instead of 2 tool calls and this also reduces thinking and token use . Basically, combining tool calls—such that a single tool call can resolve its own arguments—and not relying on the agent seems beneficial to performance . This makes the agentic AI workflow faster than before, reduces expensive GPU calls, and leads to greater user satisfaction.