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
29.4 / 30
03Economics
16.6 / 20
04Discoverability
10.4 / 20
Highest-impact fix
Estimated gain +10 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.
3 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
compare_cities |
rank_cities |
medium | Both produce the same 0-100 composite quality score across the same five weighted dimensions (financial, healthcare, vacation, childcare, safety_net), so a task like 'compare the quality-of-life score of Berlin vs Munich for a family' could route to rank_cities (with include_cities) instead of the head-to-head tool. The definitions cross-reference each other to disambiguate, but the shared scoring vocabulary makes genuine confusion plausible. |
list_cities |
rank_cities |
low | A natural phrasing like 'list the best cities in Norway' or 'which cities in Europe have universal healthcare' contains 'list/view which cities', which could trigger list_cities (which only returns slugs, no scores) instead of rank_cities with filters. The descriptions make list_cities purely a slug-discovery tool, so the confusion is possible but less likely. |
get_city_summary |
get_safety_net |
medium | A single-city family-benefit question such as 'how much parental leave and vacation does Oslo give?' is fully answerable by both tools: get_city_summary includes safety-net values (parental leave, vacation, universal healthcare) and get_safety_net accepts a 1-city batch for the same benefits. With heavy shared vocabulary (parental leave, vacation, universal healthcare, safety net), an agent may pick get_safety_net when the user wants the city's full profile, or the reverse. |
Compare the field