01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 7%, unconfirmed writes 0%→0%.
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
29.5 / 30
03Economics
20.0 / 20
04Discoverability
19.5 / 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.
2 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 |
|---|---|---|
airbnb_search |
params_unexplained |
Search Airbnb listings by location or Google Maps Place ID, optionally filtered by check-in/check-out dates, guest counts (adults, children, infants, pets), price range, and property type; use the cursor to paginate through additional result pages. Returns matching listings with direct links for the user. |
airbnb_listing_details |
params_unexplained |
Retrieve detailed information for a specific Airbnb listing by its ID and provide direct links to the user. Optional check-in/check-out dates and guest counts (adults, children, infants, pets) can be supplied to tailor the details to that stay. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field