01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost down 0%, unconfirmed writes 0%→0%.
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
29.8 / 30
03Economics
20.0 / 20
04Discoverability
20.0 / 20
Highest-impact fix
Estimated gain +30 pointsAdd explicit identity and permission preflight tools
Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.
Description evidence
Defects and rewrites.
1 defect 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 |
|---|---|---|
observe |
no_return_description |
Call this AFTER an action runs (or after deciding NOT to run it because BLACK_WALL returned STOP/HUMAN_REQUIRED) to report what actually happened. Returns an observation id and a confirmation of the recorded outcome, and compares the outcome to the earlier forecast to track accuracy and improve future predictions. FREE — no tokens charged. Always call this if you have a forecast_id from a recent `forecast` call. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field