Back to marketplace
Tool UsePersonalHorizontal
Tool Use Stress Test
Function-call scenarios your agent will eventually hit.
Function-call scenarios your agent will eventually hit. Tests tool selection, argument schema adherence, error recovery, and multi-step orchestration. MCP-compatible — reuses the same tool schemas your prod agent uses.
What's in the box.
MCP-compatible — reuses the same tool schemas your prod agent uses
Catches silent tool-call failures (valid JSON, wrong semantics)
Covers error-recovery loops and back-off behavior
InstallThree commands.
Three commands.
Then receipts.
Install the Pistachio CLI, add the harness as a Claude Code MCP tool, run it against your agent, and get a signed pass/fail report you can drop into a PR or sales deck.
CLI (Claude Code)
zsh
# 1. Install Pistachio CLI
npx @pistachio/cli login
# 2. Add the harness as a Claude Code MCP tool
pistachio harness add tool-use-stress
# 3. Run it from inside Claude Code — get a signed report
pistachio harness run tool-use-stressSDK (Node)
typescript
import { Pistachio } from "@pistachio/sdk";
const pistachio = new Pistachio({ apiKey: process.env.PISTACHIO_KEY });
const run = await pistachio.harnesses.run("tool-use-stress", {
endpoint: "https://your-agent.example.com/v1/messages",
});
console.log(run.passRate);
console.log(run.signedReportUrl);MCP-native
Lives inside Claude Code.
Signed reports
Ed25519 attestation.
Deterministic
Same input, same score.