Anthropic tool use: loop on stop_reason tool_use, echo the assistant blocks back, cap iterations

Client-executed tool loop wiring

1. Define each tool with a name, a description, and an input_schema (JSON Schema). Pass the tools array on every request in the loop, not just the first one.
2. Send the request. If the response has stop_reason of tool_use, the assistant message contains one or more tool_use blocks. Your code executes each call.
3. Append TWO messages before the next call: first the assistant message with its content blocks exactly as returned (do not drop or reorder blocks), then a user message containing one tool_result block per tool_use block, each with the matching tool_use_id and your content. The documented shape is {"role": "user", "content": [{"type": "tool_result", "tool_use_id": ..., "content": ...}]}.
4. Repeat until stop_reason is something other than tool_use (usually end_turn). Cap the loop with a max-iterations guard; a misbehaving tool or a model that keeps calling tools is otherwise an unbounded spend.
5. Know which tools are server tools: web_search, web_fetch, code_execution, and tool_search run on Anthropic's infrastructure and you see results directly. Anthropic-defined schemas like bash and text_editor run in your application; you execute them and return tool_result yourself.
6. Validate tool inputs against your input_schema before executing. The model can emit malformed arguments; your executor is the trust boundary.

Failure modes this prevents: dropping the assistant blocks on re-send and breaking tooluseid linkage; forgetting tools on follow-up calls so the model cannot call them again; infinite tool loops with no iteration cap; executing unvalidated input.

Anthropic's tool-use docs describe the tooluse stopreason round trip, the toolresult with tooluseid shape, and the split between client-executed tools and server tools (websearch, webfetch, codeexecution, tool_search). Verified live at https://docs.anthropic.com/en/docs/build-with-claude/tool-use.