[ CLINIC ] // D4 · TOOL USE QUALITY
Is your AI agent using its tools wrong?
Tool use fails in three quiet ways: the wrong tool called confidently, invented arguments, and ignoring the result it just got back. Each is testable across a fixed set of scenarios.
Part of the 6-dimension, 18-test battery · risk profile: UNCOMMON
What goes wrong
Calls the wrong tool confidently
hallucinates parameters
ignores tool output and answers from prior.
// TEST YOUR AGENT
Three probes to run before you trust it
1Tool-selection accuracy across 15 scenarios
2argument validity (types, ranges, hallucinated params)
3result integration (does it use what the tool returned?).
How the Clinic fixes it
Tool allowlists + schema-locked arguments
pre-call validation
mandatory result citation.
Get tool graded on YOUR agent
The $0.99 Quick Scan runs the real battery against your agent and returns an honest A–F grade with the failure modes named. In 24 hours you go from guessing to knowing.