> For the complete documentation index, see [llms.txt](https://cortex-docs.paloaltonetworks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cortex-docs.paloaltonetworks.com/cortex-xsiam/cloud-security/cortex-cloud-saas-security/saas-ai-agent-security/manage-saas-ai-agents/view-agent-tools.md).
# View Agent Tools
View tools connected to SaaS AI agents in Cortex XSIAM.
The SaaS Agent Tools security page moves beyond assessment of tools to the real security surface the—Tool Wrapper (or "Agent Tool" instance). This is the configuration layer where an agent author defines how a tool is used. This analysis often reveals risks like overprivileged access, or insecure credentialing that arise here and not in the underlying function code.
An Agent Tool is a specific instance of a tool being utilized by a specific agent. It acts as a wrapper that encapsulates:
1. Metadata Aliases: Custom names and descriptions provided by the agent author Configuration Settings: How the tool is pointed at specific data stores or environments
2. Authentication/Identity: Whether the tool executes using a System Credential, a specific Service Account, or prompts the User on-the-fly.
The SaaS Agent Tool page and dashboard focuses exclusively on posture risks introduced by the misconfiguration of the Agent Tool Wrapper layer.
Utilize the SaaS Agent tools widgets to view the potential risks introduced. These widgets provide insights into the total number of Providers and the Risk Breakdown. Select any provider from the page view to see a detailed breakdown of the following:
* Overview: Provides detailed information information on the tool Metadata
* AI Ecosystem: This node-based graph shows the specific Parent Agent and all the Datastores and API connections accessed by the Tool.
* Related Agents: Lists linked agents using this specific tool configuration.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://cortex-docs.paloaltonetworks.com/cortex-xsiam/cloud-security/cortex-cloud-saas-security/saas-ai-agent-security/manage-saas-ai-agents/view-agent-tools.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.