🤖 AI & LLMsAnthropicproduction

Claude API tool use: response content block is text, not tool_use, causing type error

Fresh11 days ago

Mar 14, 20260 views

Confidence Score78%

78%

Problem

When using Claude's tool use feature, code that assumes every response contains a tool_use content block crashes when Claude decides to respond with a text message instead of calling a tool. This happens when the model determines a tool call is not needed (e.g. the answer is in its context), or when max_tokens is hit before the tool call completes. The content array must always be checked for block type before accessing tool_input.

Error Output

TypeError: Cannot read properties of undefined (reading 'tool_input')
    at processResponse (src/agent.ts:42)

Unverified for your environment

Select your OS to check compatibility.

Your OS

OS version

Product version

1 Fix

Canonical Fix

High Confidence Fix

75% confidence85% success rate10 verificationsLast verified Mar 14, 2026

Check content block type before accessing tool_input

Low Risk

Claude may return a text block instead of a tool_use block when it decides a tool call is not needed. Code that directly accesses response.content[0].tool_input without checking the block type will throw.

Trust Score

10 verifications

85% success

Always check block type before accessing tool fields

Use a type guard before accessing tool_input:

typescript

const response = await anthropic.messages.create({ ... })

// ❌ Crashes when Claude responds with text
const toolInput = response.content[0].tool_input

// ✅ Type-safe access
const toolBlock = response.content.find(b => b.type === 'tool_use')
if (!toolBlock || toolBlock.type !== 'tool_use') {
  // Handle text response or unexpected response
  console.log('No tool call in response:', response.content)
  return
}
const toolInput = toolBlock.input  // safely typed

2
Use tool_choice to force a tool call when needed
If your flow requires a tool call, force it:
typescript
```
tool_choice: { type: 'tool', name: 'your_tool_name' }
```

Validation

Agent handles both tool_use and text responses without throwing.

Verification Summary

Worked: 10

Partial: 1

Failed: 2

Last verified Mar 14, 2026

Environment

Product: Claude API
Environment: production

Submitted by

Alex Chen

2450 rep