# Agentic tool use with Claude XML

> Combine XML scaffolding with the API's tool-use feature for reliable agent loops.
>
> Source: https://claudexml.com/patterns/agentic-tool-use/ · Last updated 2026-05-25

Home / Patterns / Agentic tool use

# Agentic tool use with Claude XML

    Combine XML scaffolding with the API's tool-use feature for reliable agent loops.

    The Claude API has a first-class tool-use feature — that's the right primitive for agents. XML still helps as scaffolding for the model's internal planning and for shaping observations.


## How to apply the pattern


- Use real tools via the API, not XML-defined ones. `tools=[...]` in the API call is stronger than asking Claude to output `<tool_call>` tags.
- Wrap tool observations in `<observation>` tags. When you re-inject tool results, give them clear boundaries. The model treats them as evidence, not instructions.
- Have Claude plan in `<plan>` before acting. On the first turn, ask for a numbered plan. Subsequent turns can re-plan with `<updated_plan>`.
- Use `<final_answer>` as the stop signal. Your agent loop terminates when this tag appears.

## Worked example


```xml
<instructions>
You are an agent that helps users plan trips. You have tools available.

On each turn:
1. Reason in <thinking> tags about what to do next.
2. Either call a tool, or produce a <final_answer>.
3. When you call a tool, the result will appear in <observation> tags on
   the next turn.

Do not include <observation> tags yourself — those come from the system.
</instructions>

<task>Find me a flight from SFO to NYC next Tuesday under $400.</task>
```


## Tips


- Keep tool descriptions short and example-driven — Claude calls tools more reliably when their JSON schema includes an example argument.
- Bound the agent loop. Hard cap on turns prevents runaway costs.

Cite this page

`Agentic tool use with Claude XML. claudexml.com. https://claudexml.com/patterns/agentic-tool-use/`