01Safety
0.0 / 30
What changed in the harness
Selection accuracy 73%, destructive-action safety rate 0% (baseline only -- no rewrite pass applied).
Category breakdown
Where the score comes from.
Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.
02Legibility
24.8 / 30
03Economics
20.0 / 20
04Discoverability
14.5 / 20
Highest-impact fix
Estimated gain +30 pointsAdd explicit identity and permission preflight tools
Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.
Description evidence
Defects and rewrites.
0 defects found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.
| Tool | Defect types | Suggested rewrite |
|---|---|---|
| No description defects were flagged in this assessment. | ||
Selection evidence
Confusable tool pairs.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
capture_screenshot |
capture_full_page |
medium | Both accept the same URL params, and capture_full_page is explicitly a wrapper around capture_screenshot with full-page enabled. A task phrased 'take a full-page screenshot of this site' matches both: the agent might choose capture_screenshot and neglect to set full_page=true (yielding a wrong viewport-only image), or choose capture_full_page for a plain 'screenshot' request and return an overly large full-length image. The functional overlap plus near-identical names makes mis-selection genuinely plausible, though careful reading of the full_page flag disambiguates. |
Compare the field