loading…

Think Tool

Anthropic’s think-tool technique: give the LLM a think tool that does nothing — its execute simply returns the thought argument passed to it. The value is not an action but a structured pause: the thought is appended to the message history, saving important information in context so later iterations of the tool calling loop can make better decisions.^[raw/aihero/implementing-anthropics-think-tool-in-typescript.md]

flowchart LR
    A["Complex tool call"] --> T["Think (no-op)"] --> B["Next tool call, informed"]

Mechanics

The tool is ordinary tool-calling: a description (“use it when complex reasoning or some cache memory is needed — it will not obtain new information or change the database, just append the thought to the log”) plus a JSON-schema thought: string parameter. The execute function returns the thought unchanged; persistence in the llm message protocol history does the rest. Echoes ReAct and Reflexion.

Why It Works

The model gets an explicit, schedulable slot to reflect between steps instead of cramming all reasoning into one response — a tool-surface application of the same principle behind smart zone and context staging: put the right information in the right place in history for the decision that needs it.

Failure Modes

Symptom	Root cause	Fix
Tool call storms without progress	Agent retries failing calls blindly	Force a think step after every failed call; log the diagnosis
Notes ignored on later turns	Scratchpad not re-injected	Re-inject the note summary into subsequent prompts
Think used as a delay tactic	No binding between thoughts and next action	Each thought must name the next concrete action

Rule of Thumb

One thought per decision point; a thought that does not change the next action was wasted context.

Related

tool calling loop, llm message protocol, generator evaluator loop, smart zone, context engineering.