Bug type

Regression (worked before, now fails)

Summary

name: Bug report
about: LLM tool call validation errors when parameters are missing
title: '[Bug] Tool calls fail with validation errors when required parameters are omitted'
labels: bug, tool-calling, validation
assignees: ''

Bug Description

When LLM fails to construct complete parameters during a tool call chain, it repeatedly calls the same tool (passing empty object {} or missing required parameters), resulting in repetitive validation errors. This is not an issue with individual tools, but a flaw in the tool calling mechanism's retry behavior when parameter construction fails.

Environment

Steps to Reproduce

1. Trigger a task requiring multi-step tool calls
2. During parameter construction, if LLM fails to properly populate required parameters
3. Observe the tool being called multiple times (with empty object {})
4. Each call returns the same validation error

Actual Behavior

Error Type 1: read tool missing path parameter

Missing required parameter: path alias. Supply correct parameters before retrying.

• Occurrences: 7 times
• Trigger scenario: Calling read with only empty object {}, without providing file_path or path

Error Type 2: exec tool missing command parameter

Validation failed for tool "exec": command: must have required property 'command'

• Occurrences: 10+ times
• Trigger scenario: Calling exec with only empty object {}, without providing command

Error Type 3: feishu_drive_file tool missing action parameter

Validation failed for tool "feishu_drive_file": action: must have required property 'action'

• Occurrences: 3 times
• Trigger scenario: Calling feishu_drive_file with only empty object {}, without providing action

Expected Behavior

1. Pre-validation: System should validate all required parameters are populated before sending tool calls
2. Single failure: If parameter construction fails, should error only once instead of repeatedly calling the same tool
3. Friendly hints: Error messages should guide LLM on how to correctly fill missing parameters
4. Graceful degradation: If parameters cannot be constructed, should stop current tool chain instead of retrying

Root Cause Analysis

The core issues are:

1. Fallback behavior on parameter construction failure: When LLM cannot correctly construct complex parameters, it may fallback to passing empty object {}
2. Lack of pre-validation: System does not validate parameter completeness before sending
3. Over-aggressive retry mechanism: After encountering validation errors, LLM attempts to call again but still uses the same empty parameters

Suggested Fix

Option 1: Client-side Pre-validation (Recommended)

Before sending tool call requests, system layer validates all required parameters exist:

• If missing, immediately return structured error to LLM instead of sending to tool layer
• This avoids invalid remote calls

Option 2: Error Feedback Optimization

When detecting empty parameters or missing required parameters:

• Return more detailed errors containing parameter schema information
• Prompt LLM which fields need to be filled

Option 3: Retry Limiting

For validation errors (e.g., missing required parameter):

• Limit retry count to 1
• Or require LLM to modify parameters before continuing

Additional Context

Complete Error Log Timeline

[15:16:35] read: Missing required parameter: path alias (×7)
[15:16:42] exec: Missing required property 'command' (×10+)
[15:16:48] feishu_drive_file: Missing required property 'action' (×3)

Original User Request

"Send the README.md file to my Feishu cloud drive"

This was a simple request, but triggered multiple tool call errors during execution.

Checklist

• I have checked existing issues and found no duplicates
• I have provided reproduction steps and environment information
• This is not a tool-specific issue, but a tool calling mechanism issue

Steps to reproduce

1. Trigger a task requiring multi-step tool calls
2. During parameter construction, if LLM fails to properly populate required parameters
3. Observe the tool being called multiple times (with empty object {})
4. Each call returns the same validation error

Expected behavior

1. Pre-validation: System should validate all required parameters are populated before sending tool calls
2. Single failure: If parameter construction fails, should error only once instead of repeatedly calling the same tool
3. Friendly hints: Error messages should guide LLM on how to correctly fill missing parameters
4. Graceful degradation: If parameters cannot be constructed, should stop current tool chain instead of retrying

Actual behavior

Error Type 1: read tool missing path parameter

Missing required parameter: path alias. Supply correct parameters before retrying.

• Occurrences: 7 times
• Trigger scenario: Calling read with only empty object {}, without providing file_path or path

Error Type 2: exec tool missing command parameter

Validation failed for tool "exec": command: must have required property 'command'

• Occurrences: 10+ times
• Trigger scenario: Calling exec with only empty object {}, without providing command

Error Type 3: feishu_drive_file tool missing action parameter

Validation failed for tool "feishu_drive_file": action: must have required property 'action'

• Occurrences: 3 times
• Trigger scenario: Calling feishu_drive_file with only empty object {}, without providing action

OpenClaw version

2026-03-24

Operating system

macOS Darwin 25.2.0

Install method

npm

Model

kimi/kimi-code

Provider / routing chain

openclaw-> kimi/kimi-code

Additional provider/model setup details

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response