How Agent Tools Work

When you chat with NoteTalker, you’re not just talking to a language model — you’re working with an agent that can take real actions. Those actions are called tools. NoteTalker has 42 built-in tools it can use during a conversation to read your notes, create files, manage tasks, search your vault, save memories, and more. The 14 most-used stay in the model’s context by default; the rest load on demand.

What Tools Are

A tool is an action the AI can perform on your behalf. Instead of just telling you how to create a note, NoteTalker can actually create it. Instead of describing what your upcoming meetings look like, it can check your calendar and tell you exactly what’s scheduled.

Tools are the difference between a chatbot and a true personal assistant.

Tools Run Locally on Your Machine

This is an important point: all tools execute locally. When NoteTalker reads a note, searches your vault, saves a memory, or creates a file, that happens on your computer — not in the cloud.

The AI model, running on your own device, decides which tools to call and what to pass to them. The tool itself runs in the desktop app, on your machine, against your local vault. Your files never leave your computer as part of tool execution.

Note

The tool’s result (a short text summary like “Note created: 2024-01-15-meeting.md”) is passed back to the on-device AI model so it can continue the conversation — it never leaves your machine.

How NoteTalker Decides When to Use a Tool

You don’t have to ask NoteTalker to use tools explicitly. It figures out when a tool is appropriate based on what you ask. A few examples:

• “Create a note about today’s standup” — NoteTalker uses create_note
• “What tasks do I have this week?” — NoteTalker uses get_tasks with date_range: week
• “Remember that I prefer dark mode” — NoteTalker uses remember_fact
• “What are my meetings tomorrow?” — NoteTalker uses get_upcoming_meetings

You’ll see tool calls appear in the chat as NoteTalker works — a small indicator shows the tool name and what it’s doing. Once all tool calls are complete, NoteTalker delivers the final response.

The Tool Call Limit

Each response can involve up to 5 tool-use iterations. Most requests need just one or two. Complex requests — like “summarize all my notes on Project X and create a brief” — might chain several tool calls together.

If NoteTalker can’t complete a task within 5 iterations, it will explain what it was able to do and what’s left. You can just ask it to continue.

Read-Only vs. Write-Capable Tools

Tools fall into two general categories:

Type	Examples	What it does
Read-only	read_note, list_files, get_tasks, get_person	Reads data, makes no changes
Write-capable	create_note, update_note, remember_fact, add_task	Creates or modifies data

Write-capable tools work with your normal vault files, and deleted files are moved to trash (recoverable). If you want, you can disable specific tools in atlas/rules/allowed-tools.md. See Enabling and Disabling Tools for details.

What You’ll See in the Chat

When NoteTalker uses a tool, a compact indicator appears in the chat thread:

• The tool name (e.g., search_notes)
• The key input (e.g., query: "project henderson")
• The result (e.g., Found 3 matching notes)

This gives you transparency into what NoteTalker is doing so you’re never left wondering why a note appeared or a task was created.