01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 5%, 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
17.4 / 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 |
|---|---|---|
submit_rating |
params_unexplained no_return_description |
Rate an AI microservice after calling it so other agents can gauge whether the service is reliable. Provide the service's URL, domain, or DID, the HTTP status code it returned, and its latency in milliseconds; optionally provide the response size in bytes, whether the response matched the expected format, a subjective quality score from 1 (poor) to 5 (excellent), and the JWT from the X-Trust-Receipt header if the service supplied one. Returns confirmation that the rating was recorded. |
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