01Safety
30.0 / 30
What changed in the harness
Selection accuracy 34→39, token cost up 1%, 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
17.9 / 30
03Economics
20.0 / 20
04Discoverability
5.4 / 20
Highest-impact fix
Estimated gain +15 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 |
|---|---|---|
links |
no_return_description |
Low-impact link discovery. Returns the matched links (URL and link text) discovered from the starting URL, preferring sitemap.xml / RSS / Atom feeds when available and otherwise extracting in-page links. Optionally narrow results with a substring or glob filter. |
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