cd /news/artificial-intelligence/improving-tool-use-with-small-llms · home topics artificial-intelligence article
[ARTICLE · art-88870] src=dotnetperls.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Improving Tool Use with Small LLMs

A developer using the LFM 2.5 2.6B model with llama-cpp found that adding detailed descriptions to JSON schema parameters improved tool call correctness from 0% to nearly 100%, enabling the use of a fast 1.7 GB model without a GPU for an MCP server.

read1 min views6 publishedAug 7, 2026

I have been trying to develop an agentic AI system with a local MCP server. I am using llama-cpp

with the LFM 2.5 2.6B model—this LLM is only 1.7 GB and is very fast. However I found the model used a parameter in one of the tool calls correctly about 0% of the time.

Other models, including Gemma 4, used the parameter correctly nearly 100% of the time. So I tried to figure out what the problem was. I determined that parameters in the JSON schema need to have a detailed description—describing the params in the tool call descriptions was not enough.

Here are my discoveries:

• With descriptions on the parameters specifically, tool calling was correct nearly 100% of the time in LFM 2.5 2.6B.

• It is best not to be shy about explaining how to use a parameter—a 6-line explanation is perfectly fine, and will help smaller models understand better.

It is kind of boring to write a 6-line paragraph about a tool call parameter, but it seems to really help smaller models. I went from 0% compliance on a parameter to 100% compliance—and this means I can use a small 1.7 GB model which even runs fast without a GPU for my MCP server.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @lfm 2.5 2.6b 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/improving-tool-use-w…] indexed:0 read:1min 2026-08-07 ·