01Safety
30.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 7%, 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
28.7 / 30
03Economics
20.0 / 20
04Discoverability
14.9 / 20
Highest-impact fix
Estimated gain +5 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.
3 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 |
|---|---|---|
bitcoin_price |
no_return_description |
Get the current realtime market price of bitcoin. Returns the latest bitcoin price. |
get_crypto_price |
name_restates_behavior no_return_description |
Retrieve the current realtime market price for a specified cryptocurrency using its name. Returns the latest price for the given coin. |
list_assets |
no_return_description |
Get all cryptocurrency assets available in the system. Returns the complete list of available crypto assets. |
Selection evidence
Confusable tool pairs.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
bitcoin_price |
get_crypto_price |
medium | A task like 'what is the realtime bitcoin price' plausibly matches both: bitcoin_price is specifically named for bitcoin, while get_crypto_price accepts a name parameter that could be set to 'bitcoin'. Without observing the input param, the agent could select either tool. |
Compare the field