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
29.3 / 30
03Economics
20.0 / 20
04Discoverability
19.7 / 20
Highest-impact fix
Estimated gain +1 pointRewrite 3 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.
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 |
|---|---|---|
scan |
no_return_description |
Discover all MCP server configs and test their connections via JSON-RPC handshake, returning a report of discovered configs and the pass/fail status of each connection test. |
security |
no_return_description |
Audit all MCP server configs for security issues like hardcoded secrets, tokens in args, and shell injection patterns, returning a list of findings with the affected config and issue type for each. |
doctor |
no_return_description |
Run all checks at once: scan connections, audit security, and benchmark latency for all configured MCP servers, returning a combined result with the outcome and details for each check. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field