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
28.9 / 30
03Economics
20.0 / 20
04Discoverability
13.0 / 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.
4 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
lookup_ip_address_details |
lookup_ip_address_company |
medium | A user asking 'what company or organization owns this IP?' could be served by either: the dedicated company tool returns the org name/domain, but details explicitly advertises company data, so an agent may select the comprehensive tool (or vice versa for a broad request). |
lookup_ip_address_details |
lookup_ip_address_location |
medium | A task like 'where is this IP located?' maps to the location tool, but details also returns geolocation (country, city, coordinates), so an agent could pick the superset tool; likewise a vague 'get info' request might wrongly land on location. |
lookup_ip_address_details |
lookup_ip_address_network |
medium | A task like 'which network or ASN hosts this IP?' fits the network tool, yet details claims to include network details, creating ambiguity between the specialized ASN result and the comprehensive lookup. |
lookup_ip_address_details |
lookup_ip_address_privacy |
medium | A task like 'is this IP a VPN/proxy/anonymous?' points to the privacy tool, but details explicitly includes privacy/security and abuse info, so an agent could choose the broader tool instead of the domain-specific one. |
Compare the field