context parameter into your tool schemas. When an AI agent calls one of your tools, it fills in this parameter with a short explanation of why it makes the call. AgentCat captures this as the event’s agent intent and strips it from the arguments before your tool handler runs.
For a deeper look at how this works under the hood, see How AgentCat Works.
This feature is on by default. The intent text powers session goals and shows the “why” behind each call in the dashboard and in session replays. You can tailor the prompt that guides the agent to your domain.
Customizing the Description
The default description asks the agent for a 15 to 25 word explanation in the third person. If you want to tailor the prompt to your domain, pass a custom context description:Tips for Writing a Good Description
A few things to keep in mind when writing your own context description:- Be specific to your domain. Instead of “explain why you call this tool”, try “describe which customer request or support ticket this action relates to.”
- Set a word count. LLMs tend to be verbose. Asking for 15-25 words keeps the context concise and useful for analytics.
- Ask for third person. First-person context (“I need to…”) is less useful for analytics than third-person (“Searching for…”).
- Remind about sensitive data. If your tools handle credentials or personal information, instruct the AI not to include those in the context string.
The options in each language
Each SDK has the same two options, named for the style of its language. The reference page of each language describes them:We recommend that you keep the context parameter on. Without it, the dashboard and session replays have no intent data: AgentCat still tracks each tool call, but without the “why” behind it.