01Safety
30.0 / 30
What changed in the harness
Selection accuracy 95→98, 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
27.8 / 30
03Economics
20.0 / 20
04Discoverability
19.1 / 20
Highest-impact fix
Estimated gain +1 pointRewrite 4 underspecified tool descriptions
State each tool's behavior, explain every parameter, and declare return semantics, prioritizing tools exercised by failed selection tasks.
Description evidence
Defects and rewrites.
4 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 |
|---|---|---|
reverse_dns |
no_return_description |
Perform a reverse DNS (PTR) lookup on an IP address. Returns the hostname(s) associated with the IP, or an empty result if no PTR record exists. |
resolve_all |
name_restates_behavior no_return_description |
Query a domain for its A, AAAA, MX, TXT, NS, and CNAME records in a single call instead of issuing separate lookups. Returns an object mapping each record type to its resolved values (or empty/absent if none exist). |
check_nameservers |
no_return_description |
Get the nameserver (NS) records for a domain. Returns the list of authoritative nameserver hostnames configured for the domain. |
whois |
no_return_description |
Query WHOIS data for a domain, using IANA and following referrals to registrar WHOIS servers. Returns the raw WHOIS record text, including registrar, registration/expiration dates, and nameserver information. |
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 |
|---|---|---|---|
dns_lookup |
reverse_dns |
low | dns_lookup supports a PTR record type option that overlaps conceptually with reverse_dns's purpose, but dns_lookup requires a domain input while reverse_dns requires an ip input, so a task asking to resolve an IP to a hostname would clearly need an ip parameter, making the correct tool choice fairly unambiguous despite the shared PTR concept. |
Compare the field