project

Toolmetry

Open-source project that measures how well language-model agents use MCP tools and rewrites tool descriptions to improve them; it ships measure, optimize and proxy commands, the last of which rewrites descriptions in flight.

Current clusters

build1 publisher

A $4 rewrite of MCP tool descriptions moved Toolmetry's SQLite success from 34% to 100%

Toolmetry edited only the strings that tell an agent what each MCP tool does and how to call it. On a single published run, its three test servers finished between 96.4 and 100 percent for $4 of API spend.

Publishers:dev.to

Reality

Evidence30
Adoption: Insufficient
Hype gap+55
Incentives55
Confidence38