implementation detail · filed under inference & serving
Typed tool arguments
Tool arguments use typed representations with a pure-JSON fallback for arguments that cannot be decomposed.
Also called Arguments are typed.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Arguments are typed: string arguments appear as raw text, while values of other JSON types are compactly serialized. A pure-JSON fallback block covers inputs whose arguments cannot be decomposed into typed argument blocks; it occurs only in input tokens, never in model outputs, and its loss is masked during training.
usedsoftware implementationin Kimi K3Moonshot AI
Filed alongside
Other methods under inference & serving :: agentic scaffolding.
Advisor strategyAutomatic tool choicePython toolFunction callingHarmony formatBrowser toolGeneric tool-call parserMCP tool configurationMulti-agent collaborationRole-based instruction hierarchyThinking with toolsVisual Search ToolXML-based tool-call schema with DSML tokenAgent Team modeAgentENVAgentic searchAgentic tool callingApp-server mode with adapted tool schemasAppArmor and eBPF sandbox policiesAssistant output channelsAsynchronous teammate spawningBash commands for context retrievalBash computer-use agentBrowsing tool with domain filtering