Tidepool Toys
toys · 10 audit runs · task: find a product and add it to the cart · sample data (illustrative fixture, not a real measurement)
Readiness score
100/100
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
40% · avg 14 steps
Agent success via WebMCP tools
100% · avg 4 steps
Why runs fail here
navigation loop1 of 3
captcha1 of 3
timeout1 of 3
Run log
FAIL ui 13 steps 109.3s navigation_loop
FAIL ui 19 steps 137.4s captcha
PASS ui 15 steps 48.0s
FAIL ui 15 steps 90.6s timeout
PASS ui 13 steps 41.6s
PASS webmcp 3 steps 9.6s
PASS webmcp 2 steps 6.4s
PASS webmcp 5 steps 16.0s
PASS webmcp 6 steps 19.2s
PASS webmcp 3 steps 9.6s