01Safety
30.0 / 30
What changed in the harness
Selection accuracy 100%, 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
29.6 / 30
03Economics
20.0 / 20
04Discoverability
11.7 / 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 |
|---|---|---|---|
get_news |
get_news_detail |
medium | Names differ only by 'detail' and a task like 'get me the news details' or 'tell me more about the news' can map to either; an agent may pick get_news_detail even though it requires an event_id and returns a single event, while get_news itself advertises deep-diving into an event when the user asks for detail, blurring the boundary. |
get_news |
get_topics |
low | A request such as 'show me the current news topics' is ambiguous between listing topic slug categories (get_topics) and fetching news stories around a topic (get_news with a topics param); the shared 'news' token plus the topics filter on get_news makes picking the wrong one plausible. |
Compare the field