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
29.7 / 30
03Economics
20.0 / 20
04Discoverability
17.2 / 20
Highest-impact fix
Estimated gain +3 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.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
where_to_watch |
whats_new_on |
medium | A task like 'where can I watch the latest movies in India' or 'what's new to watch on streaming in Japan' blends recency/discovery ('latest', 'new') with a 'where can I watch' phrasing. The 'where to watch' wording pulls an agent toward where_to_watch, but there is no specific title (a required input), while whats_new_on needs a provider slug the user didn't give. Neither description cleanly covers 'what's newly streaming in country X without a named title or provider', so an agent can select the wrong one. |
Compare the field