01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, 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
29.5 / 30
03Economics
20.0 / 20
04Discoverability
8.6 / 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 |
|---|---|---|
growthbook_list_skills |
no_return_description |
List available GrowthBook agent skills, returning each skill's name and description. Use growthbook_read_skill to load the full workflow for a skill before acting. Skills encode how to accomplish GrowthBook tasks well; use growthbook_call_api to execute the REST calls they describe. |
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 |
|---|---|---|---|
growthbook_list_skills |
growthbook_read_skill |
medium | A task like 'show me how to launch an experiment in GrowthBook' could lead an agent to call read_skill directly with a guessed name instead of first listing skills to discover the exact name, or to stop at list_skills thinking the summary description is sufficient without loading the full workflow. |
Compare the field