The "think" tool: Enabling Claude to stop and think in complex tool use situations
Source
Anthropic
Author
Anthropic
Date
Terms in this piece · Glossary
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Adding a no-op 'think' tool gives Claude an explicit checkpoint to reason through policies and multi-step tool chains, measurably improving reliability on complex agentic tasks — a cheap, easy pattern to drop into any AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → that uses tools.
Key quotes
“Airline domain : The "think" tool with an optimized prompt achieved 0.570 on the pass^1 metric, compared to just 0.370 for the baseline—a 54% relative improvement;”
Anthropic
“Extended thinking is all about what Claude does before it starts generating a response. With extended thinking, Claude deeply considers and iterates on its plan before taking action. The "think" tool is for Claude, once it starts generating a response, to add a step to stop and think about whether it has all the information it needs to move forward.”
Anthropic
“Our experiments ( n =30 samples with "think" tool, n =144 samples without) showed the isolated effects of including this tool improved performance by 1.6% on average (Welch's t -test: t (38.89) = 6.71, p < .001, d = 1.47).”
Anthropic
“We found that, when they were long and/or complex, including instructions about the "think" tool in the system prompt was more effective than placing them in the tool description itself.”
Anthropic
“Extended thinking capabilities have improved since its initial release, such that we recommend using that feature instead of a dedicated think tool in most cases.”
