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
28.5 / 30
03Economics
19.8 / 20
04Discoverability
12.8 / 20
Highest-impact fix
Estimated gain +7 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.
5 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
op3_episode_downloads |
op3_downloads_timeseries |
high | op3_downloads_timeseries explicitly advertises 'filter by episode', so a task like 'list download counts for each episode of my show' could wrongly pick the raw-record tool instead of op3_episode_downloads. |
op3_get_show |
op3_show_downloads |
medium | op3_get_show returns a stats page URL and optional episode list, so a task phrased as 'get my show's stats/download summary' could wrongly resolve to the show lookup instead of the download-summary tool. |
op3_show_downloads |
op3_downloads_timeseries |
medium | A task like 'get download history/numbers for my show over a date window' could map either to the weekly/monthly summary (op3_show_downloads) or to raw records (op3_downloads_timeseries); both cover recent/windowed downloads. |
op3_show_downloads |
op3_episode_downloads |
medium | Both return download counts for the same show, and vague requests like 'show me recent downloads for my podcast' don't signal whether the user wants the show-level weekly summary or per-episode counts. |
op3_top_apps |
op3_top_countries |
medium | Both return top-ranked lists with download counts and percent share, so a task such as 'what are the top downloaders/sources for my show' could be interpreted as apps or as countries. |
Compare the field