Skip to content

docs: clarify think tool is for models without native reasoning #2191

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
dgageot merged 1 commit into from
Mar 20, 2026
Merged

docs: clarify think tool is for models without native reasoning #2191

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/concepts/multi-agent/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,7 +211,7 @@ toolsets:
- **Keep agents focused** — Each agent should have a clear, narrow role
- **Write clear descriptions** — The coordinator uses descriptions to decide who to delegate to
- **Give minimal tools** — Only give each agent the tools it needs for its specific role
- **Use the think tool** — Give coordinators the think tool so they reason about delegation
- **Use the think tool when needed** — For models without native reasoning, give coordinators the think tool so they reason about delegation. Models with built-in thinking (e.g., via `thinking_budget`) don't need it
- **Use the right model** — Use capable models for complex reasoning, cheap models for simple tasks

<div class="callout callout-info">
Expand Down
8 changes: 4 additions & 4 deletions docs/guides/tips/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,16 +169,16 @@ agents:
- Order by preference (best first)
- Include a cheaper/faster model as last resort

### Use Think Tool for Complex Tasks
### Use Think Tool for Non-Reasoning Models

The `think` tool dramatically improves reasoning quality with minimal overhead:
The `think` tool provides a reasoning scratchpad for models that lack built-in thinking capabilities:

```yaml
toolsets:
- type: think # Always include for complex agents
- type: think # Useful for models without native reasoning
```

The agent uses it as a scratchpad for planning and decision-making.
The agent uses it as a scratchpad for planning and decision-making. If your model already supports a [thinking budget]({{ '/configuration/models/#thinking-budget' | relative_url }}) (e.g., Claude with extended thinking, OpenAI o-series, Gemini with thinking enabled), you don't need this tool — the model can reason internally.
Copy link

@docker-agent docker-agent bot Mar 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same terminology issue in tips documentation

This line also uses "extended thinking" and "o-series" which are not found in the provider documentation. Please use the same terminology as documented in docs/providers/anthropic/index.md and docs/providers/openai/index.md.


## Security Tips

Expand Down
6 changes: 3 additions & 3 deletions docs/tools/think/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ _Step-by-step reasoning scratchpad for planning and decision-making._

The think tool is a reasoning scratchpad that lets agents think step-by-step before acting. The agent can write its thoughts without producing visible output to the user — ideal for planning complex tasks, breaking down problems, and reasoning through multi-step solutions.

This is a lightweight tool with no side effects. It's recommended for all agents — it improves the quality of reasoning on complex tasks at minimal cost.
This is a lightweight tool with no side effects. It is most useful for models that lack built-in reasoning or thinking capabilities (e.g., smaller or older models). For models that already support native thinking — such as Claude with extended thinking, OpenAI o-series, or Gemini with a thinking budget — this tool is unnecessary since the model can reason internally.
Copy link

@docker-agent docker-agent bot Mar 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Terminology inconsistency with provider documentation

The term "extended thinking" is not used in the Anthropic provider documentation. The docs at docs/providers/anthropic/index.md refer to this feature as "Thinking Budget" and "Interleaved Thinking".

Similarly, "OpenAI o-series" is not documented anywhere in docs/providers/openai/index.md. The OpenAI provider docs list models like gpt-5, gpt-5-mini, gpt-4o, and gpt-4o-mini with thinking budget support, but no "o-series".

Suggestion: Use terminology consistent with the provider documentation:

  • For Claude: "Claude with Thinking Budget" or "Claude Sonnet 4.5"
  • For OpenAI: Refer to specific models like "gpt-5" or "gpt-5-mini" instead of "o-series"
  • Consider linking to the provider docs for clarity


## Configuration

Expand All @@ -24,7 +24,7 @@ toolsets:
No configuration options.

<div class="callout callout-tip">
<div class="callout-title">💡 Tip
<div class="callout-title">💡 When to use
</div>
<p>Include the think tool in every agent. It adds minimal overhead while significantly improving reasoning quality on complex tasks.</p>
<p>Use the think tool with models that don't have native reasoning capabilities. If your model already supports a <a href="{{ '/configuration/models/#thinking-budget' | relative_url }}">thinking budget</a>, you likely don't need this tool.</p>
</div>
Loading