# Reasoning - should it use a tool?

**URL:** <https://community.crewai.com/t/reasoning-should-it-use-a-tool/7179>\
**Category:** CrewAI Community Support\
**Tags:** crewai\
**Created:** [November 6, 2025, 7:07pm UTC](https://community.crewai.com/t/reasoning-should-it-use-a-tool/7179 "2025-11-06T19:07:22Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![crew\_193](https://avatars.discourse-cdn.com/v4/letter/c/c67d28/32.png) [@crew\_193](https://community.crewai.com/u/crew_193)\
**Post date:** [November 6, 2025, 7:07pm UTC](https://community.crewai.com/t/reasoning-should-it-use-a-tool/7179/1 "2025-11-06T19:07:22Z")

</div>

This is using gpt-oss:120b throught vLLM.

I enabled reasoning for an Agent. Sometimes I see it’s using a tool (`Used create_reasoning_plan (1)`) and sometimes not. How is this decision made? I looked at the documentation but couldn’t find anything related to that tool.

```auto
🚀 Crew: crew
├── 📋 Task: extractor_task (ID: 09b4162c-f6ee-4d54-a797-011cf285bd6f)
│ Assigned to: Device, interface and time extractor
│   
│ Status: ✅ Completed
│ ├── ✅ Reasoning Completed
│ ├── 🔧 Used create_reasoning_plan (1)
│ └── ✅ Knowledge Retrieval Completed
├── ✅ Knowledge Retrieval Completed
└── 📋 Task: elasticsearch_lldp_task (ID: 7e21214b-756d-4a75-b026-9559f417b0ca)
    Assigned to: You are an expert in Elasticsearch Query DSL.
    
    Status: ✅ Completed

```

Other times (most of the time), I see the following:

```auto
🚀 Crew: crew
├── 📋 Task: extractor_task (ID: df19f2b6-b808-4709-bf39-0ec55bfff2ee)
│ Assigned to: Device, interface and time extractor
│   
│ Status: ✅ Completed
│ ├── ✅ Reasoning Completed
│ └── ✅ Knowledge Retrieval Completed
├── ✅ Knowledge Retrieval Completed
└── 📋 Task: elasticsearch_lldp_task (ID: a01183b9-6c37-451d-b818-d7bec25a6523)
    Assigned to: You are an expert in Elasticsearch Query DSL.
    
    Status: ✅ Completed

```

In both cases, the reasoning plan looked good but the task failed to abide by the plan and/or hallucinate.