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
29.6 / 30
03Economics
20.0 / 20
04Discoverability
17.1 / 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.
2 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
search_gaps |
get_viral_social_gaps |
medium | Both tools return buildable 'gaps', and the viral tool's description even warns against using it for general 'find me ideas'/'what should I build' queries. A task like 'find trending TikTok build ideas' or 'what viral consumer opportunities should I build' weights 'find/build/ideas' toward search_gaps and 'viral/TikTok/trend' toward get_viral_social_gaps, so the agent could pick the wrong one. |
get_viral_social_gaps |
get_stats |
low | A task like 'give me the stats on viral gaps' or 'what are the viral trend stats right now' is ambiguous between the database-statistics tool (get_stats has no gap-specific filtering) and the tool that actually returns viral trend gap data, so 'stats' as a vague keyword could route to the wrong member. |
Compare the field