01Safety
30.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 2%, 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
29.1 / 30
03Economics
20.0 / 20
04Discoverability
19.4 / 20
Highest-impact fix
Estimated gain +1 pointRewrite 1 underspecified tool description
State each tool's behavior, explain every parameter, and declare return semantics, prioritizing tools exercised by failed selection tasks.
Description evidence
Defects and rewrites.
1 defect 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 |
|---|---|---|
explore_name |
no_return_description |
Explore a name across multiple TLDs (.com, .io, .ai, .co, .dev, .app, .net, .xyz, .org) and return which domain variations are available, including availability status and pricing for each, so you can quickly spot strong options when brainstorming domain names for a new project. Powered by AgentDomainService.com. |
Selection evidence
Confusable tool pairs.
3 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
brainstorm_domains |
analyze_domain |
medium | A task like 'analyze some good domain names for my AI recipe app' maps the word 'analyze' to analyze_domain, but the provided input is a project description, not a specific domain, so an agent could call analyze_domain with a description it can't process instead of brainstorm_domains. |
check_domain |
analyze_domain |
medium | Both take a concrete domain string and a task like 'check this domain, is it a good one?' is genuinely ambiguous: check_domain returns availability/pricing while analyze_domain judges brandability and quality, and the word 'check' naturally points to check_domain even when the user wants an evaluation. |
check_domain |
brainstorm_domains |
low | check_domain requires a specific domain string while brainstorm_domains takes a description; a realistic task either names a concrete domain (unambiguous) or describes a concept, and the schema mismatch makes wrong selection unlikely since no domain is supplied for check_domain to act on. |
Compare the field