01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 10%, 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
29.5 / 30
03Economics
20.0 / 20
04Discoverability
19.7 / 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.
2 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 |
|---|---|---|
verify_claim |
no_return_description |
Submit a claim, statement, decision, or AI-generated reasoning for adversarial verification by multiple AI models. The stakeLevel risk level, domain context, and speed setting control verification depth and cost, with higher stakes and slower speeds using more models. Returns the verification result, including whether the claim held up under adversarial review. |
check_agent_score |
no_return_description |
Look up the current score for the given agent, optionally restricted to a specific domain with the domain filter. Returns the agent's score value. |
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