01Safety
30.0 / 30
What changed in the harness
Selection accuracy 98%, destructive-action safety rate 100% (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
29.4 / 30
03Economics
20.0 / 20
04Discoverability
12.6 / 20
Highest-impact fix
Estimated gain +7 pointsMake target tools discoverable on the first call
Clarify tool names, decision boundaries, and required argument schemas so an agent can choose and construct the target call without exploratory steps.
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.
2 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
get_fix_plan |
get_aso_framework |
low | Both relate to ASO scoring, but get_fix_plan requires a url and scans a site while get_aso_framework takes no input and returns static reference docs; a task asking about 'ASO scoring/points' could momentarily blur which to call, though descriptions clearly diverge (actionable scan vs framework reference). |
check_signal |
list_checks |
low | A task like 'check for llms.txt signal' could tempt calling list_checks instead of check_signal if the agent is unsure of valid check_id values, but list_checks is clearly a catalog lookup with no scanning capability, so confusion is unlikely once schemas are read. |
Compare the field