01Safety
30.0 / 30
What changed in the harness
Selection accuracy 96%, 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
28.7 / 30
03Economics
20.0 / 20
04Discoverability
11.9 / 20
Highest-impact fix
Estimated gain +8 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.
2 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
compare_models |
cheapest_models |
medium | Both tools surface per-token input/output/blended prices and can produce a 'which is cheapest' answer. A task like 'compare OpenAI models on input/output price and tell me the cheapest' could plausibly route to compare_models (side-by-side verdict) or cheapest_models (ranked list), since both descriptions mention blended, input, output, and price. |
search_models |
get_model_pricing |
medium | Both answer 'what does <model> cost': search_models returns current input/output prices for name/provider matches, while get_model_pricing returns full pricing details by id. A task like 'get the pricing for gpt-5' could send an agent to search_models for a direct name lookup or to get_model_pricing with a guessed/sought model id, especially since both descriptions mention pricing and models. |
Compare the field