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
29.3 / 30
03Economics
3.4 / 20
04Discoverability
17.1 / 20
Highest-impact fix
Estimated gain +17 pointsReduce the tool-definition and task token payload
Consolidate overlapping tools and trim repetitive schema text while preserving behavior, parameter, and return semantics.
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 |
|---|---|---|---|
amt_iso_optimize |
rsu_lot_optimize |
medium | Both are multi-year, tax-minimizing equity-compensation scheduling tools ('optimized schedule', 'which years', 'lowest tax'), so a vague task like 'when should I sell my company stock to minimize taxes' or 'optimize the tax schedule on my equity grants' could pull the agent to either. The confusion is genuine but bounded: each description leads with its asset class (ISO exercise/AMT vs. vested RSU lot divestment) and the word 'options' tilts toward amt_iso_optimize even for users whose actual holding is RSU lots, so tasks that omit the grant type are the real risk. |
Compare the field