01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100%, destructive-action safety rate 0% (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
29.7 / 30
03Economics
17.8 / 20
04Discoverability
16.1 / 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.
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 |
|---|---|---|---|
list_jobs |
list_job_types |
medium | A user asking 'what jobs can I do/run?' or 'what jobs are available' is ambiguous: list_jobs returns the account's past jobs, while list_job_types returns the available job type catalog. Both are read-only list operations sharing the 'list' and 'job' tokens, so an agent could pick the wrong one for capability-type questions. |
Compare the field