01Safety
30.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 3%, unconfirmed writes 100%→100%.
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
29.8 / 30
03Economics
20.0 / 20
04Discoverability
17.9 / 20
Highest-impact fix
Estimated gain +2 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.
1 defect 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 |
|---|---|---|
find_sources |
params_unexplained |
Multi-engine news/source search (Google News, GDELT, Hacker News) for a query: returns a deduped list of {outlet, domain, url, date}. Use when you want raw coverage to judge yourself, not a scored verdict — the cheaper primitive under corroborate_claim. query is the search query or claim to find sources for; window_days limits the lookback window in days; max_sources caps how many evidence sources are returned. Keyless, read-only. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field