Saffron Basket Foods
grocery · 5 audit runs · task: find a product and add it to the cart · sample data (illustrative fixture, not a real measurement)
Readiness score
48/100
70% task success · 15% WebMCP tool surface · 15% efficiency (steps to complete). Full rubric in the open methodology.
The WebMCP delta
Agent success via raw UI
60% · avg 14 steps
Agent success via WebMCP tools
No WebMCP tools exposed — this is the opportunity.
Why runs fail here
ambiguous ui2 of 2
Run log
FAIL ui 18 steps 144.2s ambiguous_ui
PASS ui 11 steps 35.2s
PASS ui 16 steps 51.2s
FAIL ui 19 steps 147.1s ambiguous_ui
PASS ui 15 steps 48.0s