01Safety
0.0 / 30
What changed in the harness
Selection accuracy 93→98, token cost up 1%, unconfirmed writes 0%→0%.
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
28.5 / 30
03Economics
20.0 / 20
04Discoverability
12.5 / 20
Highest-impact fix
Estimated gain +30 pointsAdd explicit identity and permission preflight tools
Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.
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 |
|---|---|---|
setup_ghl_mcp |
no_return_description |
First-run setup for GHL Command MCP. Validates your license and GHL credentials, then writes them to a per-user credentials file. Returns confirmation of what was validated and saved, and reports the resulting tool counts. After it completes, restart Claude to load all 233 tools (179 if you skip the optional Firebase fields; add Firebase later with enable_workflow_builder). |
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