01Safety
30.0 / 30
What changed in the harness
Selection accuracy 93%, 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
28.4 / 30
03Economics
20.0 / 20
04Discoverability
14.3 / 20
Highest-impact fix
Estimated gain +6 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.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
scan_mcp_config_path |
scan_mcp_config_json |
medium | Both tools scan MCP config and never execute the server, so a natural-language task like 'scan my MCP config and flag suspicious servers' gives no surface hint about input format. If the user mentions a file path, `scan_mcp_config_path` fits; if they paste raw JSON, `scan_mcp_config_json` fits. An ambiguous phrasing (config on disk vs. config text, or a request for a 'report' vs. compact decisions) could lead the agent to pick the wrong one since only the input-type keywords (path/json) and output shape differ. |
Compare the field