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.
01Safety
02Legibility
29.1 / 30
03Economics
20.0 / 20
04Discoverability
16.4 / 20
Highest-impact fix
Estimated gain +4 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.
4 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
get_balance_sheet |
get_cash_flow |
medium | Cash appears on both statements: cash & equivalents on the balance sheet versus operating/investing/financing cash flows, so a task like 'how much cash does Apple have' could plausibly route to either tool. |
get_income_statement |
get_metrics |
medium | Both cover profitability: the income statement reports net income while metrics reports net/operating margins, so a task asking for 'net profit' or 'profitability' is ambiguous between a raw figure and a ratio. |
get_cash_flow |
get_metrics |
medium | Free cash flow only appears as FCF margin in get_metrics, but a user asking 'what is Apple's free cash flow' is likely to match the get_cash_flow name and end up on the wrong tool. |
get_balance_sheet |
get_metrics |
low | The term 'equity' appears in both descriptions (balance sheet equity section vs debt/equity ratio in metrics), so a leverage or equity-magnitude task could send the agent to the wrong tool. |
Compare the field