Agents
Tools
Tools are the actions an agent can take during a turn. You choose which ones it's allowed to use; the model decides when to call them.
Enabling tools
List the tool names in the agent's tools field. A tool is only useful if the agent also has what it needs: kraterion_search requires a knowledge-enabled bucket, and the read/write tools require the relevant bucket to be attached and granted to the agent's sub-wallet.
The eight tools
| Tool | Kind | Args | Does |
|---|---|---|---|
kraterion_search | read | bucket, query, top_k? | Hybrid keyword + vector search over a knowledge-enabled bucket. |
kraterion_list_buckets | read | — | List the buckets attached to the agent. |
kraterion_list_objects | read | bucket, prefix?, limit? | List object keys in a bucket. |
kraterion_read_object | read | bucket, key | Read an object's contents. |
kraterion_write_object | write | bucket, key, content, content_type? | Create or overwrite an object. |
kraterion_get_manifest | read | bucket, key | Fetch an object's knowledge manifest (chunks, hashes, blob ids). |
memory_remember | write | content | Save a fact to the agent's memory. |
memory_recall | read | query | Retrieve relevant facts from the agent's memory. |
Read vs write
Read tools observe your data and have no side effects. Write tools change it: kraterion_write_object stores a new object — which encrypts the bytes, uploads them to Walrus, and records the result on-chain — and memory_remember appends to the agent's memory. Grant write tools only to agents you intend to let modify storage.
Tool-call trace
Every tool the agent calls during a turn is surfaced in the chat response, under the kraterion.tool_calls field (and as streaming kraterion.tool_call frames). Write tools that touch storage include the resulting on-chain transaction and Walrus blob ids, so an answer that changed something is traceable end to end. See the Chat API for the exact shape.