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
19.8 / 20
04Discoverability
15.0 / 20
Highest-impact fix
Estimated gain +5 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.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
getBaziChart |
getHuangli |
medium | A natural query like '看看今天这个日子的八字' or 'today's bazi/四柱 for the day' straddles both tools: the name getBaziChart directly matches '八字', yet getBaziChart requires a person's birth date/time/gender to build a full chart, whereas getHuangli is what actually returns the day's 干支, 宜忌, and 流日. Both accept year/month/day, and 'bazi' appears in both descriptions (getHuangli mentions staying consistent with 八字 流日), so a date-only query mentioning 八字 could misroute the agent to getBaziChart, which would then fail or force fabricated birth parameters. |
Compare the field