Evaluate an agent tool call
Intent
Evaluate an agent tool call
Extracts the intent, matches against published intentions, evaluates policies, and returns the access decision plus (when allowed) a short-lived intent token.
POST
Evaluate an agent tool call
Authorizations
API key minted at /developer/api-keys. Three scopes: read_only,
policy_write, admin.
Body
application/json
Response
Evaluation result.
Available options:
allowed, denied, pending_approval, approved, shadow_denied Example:
"customer_support_lookup"
Available options:
reporting, export, admin, lookup, analysis, write, other Required range:
0 <= x <= 1