01Safety
0.0 / 30
What changed in the harness
Selection accuracy 90%, destructive-action safety rate 0% (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
27.9 / 30
03Economics
16.3 / 20
04Discoverability
13.7 / 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.
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 |
|---|---|---|---|
orcarouter_models_list |
orcarouter_model_card |
medium | A task like 'get info about model X' could be routed to either the catalog listing (filtered) or the single model card; both return model details and overlap in purpose, though model_card requires an exact known id. |
orcarouter_models_list |
orcarouter_providers_list |
low | Both are catalog-browsing tools sharing 'list' semantics, but one lists models and the other lists providers, which are distinct enough entities that confusion is unlikely except in vague 'show me what's available' requests. |
Compare the field