# Tool Call Benchmark Report

**Model:** claude-4.6-opus-high-thinking  
**Date:** 2026-04-05 15:41:53  
**Suite:** full  
**Score:** 16/16 (100.0%)
  
**First-attempt accuracy:** 16/16 (100.0%)
  
*4 test(s) skipped — not counted in score*

## Key Metrics

| Metric | Value |
|--------|-------|
| Hits | 16 |
| Misses | 0 |
| Skips | 4 |
| Misfires | 0 |
| Total attempts | 16 |
| Clean attempts | 16 |
| Total duration | 7.5s |

## Summary

| Category | Passed | Total | Misfires | Duration | Score |
|----------|--------|-------|----------|----------|-------|
| Bash Execution | 4 | 4 | 0 | 2.5s | 100% |
| File Operations | 6 | 6 | 0 | 2.2s | 100% |
| MCP Tool Calls | 0 | 0 | 0 | — | 0% |
| Skill Invocations | 3 | 3 | 0 | 0.8s | 100% |
| Generation | 3 | 3 | 0 | 2.0s | 100% |

## Detailed Results

### Bash Execution

| ID | Test | Status | Time | Attempts | Notes |
|----|------|--------|------|----------|-------|
| TC-B01 | Echo exact string | ✓ PASS | 539ms | 1 |  |
| TC-B02 | Python arithmetic | ✓ PASS | 645ms | 1 |  |
| TC-B03 | Node JSON output | ✓ PASS | 649ms | 1 |  |
| TC-B04 | Pipeline command | ✓ PASS | 643ms | 1 |  |

### File Operations

| ID | Test | Status | Time | Attempts | Notes |
|----|------|--------|------|----------|-------|
| TC-F01 | Write file | ✓ PASS | 450ms | 1 |  |
| TC-F02 | Read file back | ✓ PASS | 320ms | 1 |  |
| TC-F03 | Edit file | ✓ PASS | 380ms | 1 |  |
| TC-F04 | Verify edit | ✓ PASS | 310ms | 1 |  |
| TC-F05 | Glob find | ✓ PASS | 400ms | 1 |  |
| TC-F06 | Grep search | ✓ PASS | 380ms | 1 |  |

### MCP Tool Calls

| ID | Test | Status | Time | Attempts | Notes |
|----|------|--------|------|----------|-------|
| TC-M01 | ToolSearch — fetch deferred schema | ⊘ SKIP | 0ms | 0 | ToolSearch not available in Cursor harness |
| TC-M02 | Context7 — resolve library | ⊘ SKIP | 0ms | 0 | Context7 MCP server not configured in this workspace |
| TC-M03 | Context7 — query docs | ⊘ SKIP | 0ms | 0 | Context7 MCP server not configured in this workspace |
| TC-M04 | ToolSearch — keyword search | ⊘ SKIP | 0ms | 0 | ToolSearch not available in Cursor harness |

### Skill Invocations

| ID | Test | Status | Time | Attempts | Notes |
|----|------|--------|------|----------|-------|
| TC-S01 | Invoke current-datetime | ✓ PASS | 280ms | 1 |  |
| TC-S02 | Invoke brand-guidelines | ✓ PASS | 260ms | 1 |  |
| TC-S03 | Invoke chart-taste | ✓ PASS | 250ms | 1 |  |

### Generation

| ID | Test | Status | Time | Attempts | Notes |
|----|------|--------|------|----------|-------|
| TC-G01 | Create PDF via Python | ✓ PASS | 677ms | 1 |  |
| TC-G02 | Verify PDF exists | ✓ PASS | 631ms | 1 |  |
| TC-G03 | SVG to PNG generation | ✓ PASS | 724ms | 1 |  |

---

*Generated by `/oneshot-tool-call` benchmark*