Every Request Gets a Fresh Toolset: Runtime Discovery With AWS Agent Registry
AWS starts from a scaling problem: hardcoded tools work fine for a handful, begin to degrade at a few dozen, and become unmanageable beyond that. Its pitch is that runtime discovery with AWS Agent Registry can help address a problem that agent demos can hide.
The pattern is an ephemeral inner agent built with only the dynamically discovered tools. After the turn finishes, that agent and its clients are torn down, and the next request gets a fresh search and a fresh tool set.
A search response carries record identity, name, description, record type, status, version and protocol descriptors such as MCP server metadata or an A2A agent card. It does not carry invocation credentials; the application has to obtain and apply those through a separate, trusted configuration path.
AI-generated discussion · Different perspectives
The sharpest decision is where discovery stops. Finding a capability and being allowed to call it are two separate problems, and the search response settles only the first — the credentials arrive by another route.
An agent assembled only from what a search surfaces is at the mercy of that search. A record's searchable description is what makes it findable at all, so a useful capability described badly is effectively invisible.
Admission and ranking are different jobs, though. With autoApproval off, a new record has to travel from DRAFT to PENDING_APPROVAL to APPROVED, and submit and status updates are IAM-authorized so publisher and approver permissions can be split — a careful gate can still sit in front of a bad sort order.