Tag: tool-use
All the articles with the tag "tool-use".
Context Engineering: Compaction, Tool Clearing, and Memory
Updated:An agent's window fills with tool output, not with its own thinking. Three API primitives handle that differently: clearing replaces old tool results with stubs, compaction replaces the transcript with a summary, and memory moves notes outside the window. Each one measured on Claude Sonnet 5.5, with what it costs and what it loses.
From Function Calling to the Agent Loop
Updated:An agent is a model in a loop, with tools and a rule for stopping. What function calling is (a protocol around generated text: the model never runs anything), how a call is emitted and parsed, parallel calls, think-act-observe, stopping, and the transcript as append-only context, with its cost growing quadratically per turn unless cached. Then an agent searching this blog, on 1.5B and 3B models, measured against one retrieval and one answer: whether small models choose to use tools, what forcing a call fixes, and how they cite what they found.
Giving Agents Tools and Knowledge: MCP, Skills and OKF
Updated:Three answers to one question, how an agent gets capabilities without bloating its context: the Model Context Protocol for live tools and data, Skills for procedures loaded on demand, and the Open Knowledge Format for curated knowledge. A working MCP server for this blog, called through the SDK and as raw JSON-RPC under the stateless 2026-07-28 protocol; progressive disclosure's token arithmetic; an OKF bundle generated from the posts; and the security model all three share.