Equipping Tools

Tools are an agent’s capabilities. Too many slows it down and raises cost; too few prevents it from finishing the job. Picking the right set matters.

How to enable tools

Open the agent → Settings tab
In the Enabled Tools section, toggle the ones you need
Use the Auto Execute / Approval Required button next to each tool to set whether the agent must request approval before running it (risky tools default to Approval Required)
Save

💡 Recommended: 30 or fewer tools per agent. If you need more, break the work into a team — each team-member agent can carry a different tool set.

Common tool categories

Category	Tools
🌐 Info gathering	Web Search · HTTP Request · Web Browser
✍️ Output	Notify User · Send Card · Ask User · Share File · Canvas Create/Update · Canvas List
💾 Memory/files	Read File · Write File · Edit File · Memory Scan · History Search · History Read
💻 Code/system	Bash · Computer Use
⏰ Automation	Schedule Create/List/Update/Delete · Task Create/Update/List
👥 Team collaboration	Team Agent List · Team Agent Create · Team Agent Equip · Team Chat Send/Read · Team State Get/Set/List/Delete · Sub Agent Spawn
🧩 Skills	Skill Search · Skill Inspect · Skill Install/Activate · Skill Execute · Skill Export · Skill Feedback · Skill Patch
🎨 Creative	Image Generate · Agent Set Avatar

🌐 Information gathering

Settings label	When to use
Web Search	When you need to search the web by keyword (with optional domain allow/block lists). Automatically combines multiple search engines and breaks complex queries into sub-searches, returning results with citations
HTTP Request	When you know the URL and need to call an external API or fetch a static page — supports custom methods, auth headers, and request bodies
Web Browser	Sites that require login, clicks, scrolling, or input. Whether a click auto-proceeds or shows an approval card depends on what the target element does — a “Post” or “Pay” button always asks; opening a menu does not. See Handling Approvals for the full breakdown

Tip: For quickly pulling information, web search is the lighter, faster option. Reach for Web Browser when you need to work a site directly — login, clicks, or typing. You can also grant both and let the agent pick whichever fits the task.

✍️ Output

Settings label	When to use
Notify User	Sends a message and push notification to the user during autonomous runs (schedule / mention / webhook). Not exposed when the user is actively in a conversation session
Send Card	Attach a structured card (info card, OAuth connect, file picker, etc.) alongside a message. Available in all trigger types
Ask User	Ask the user a question mid-flight and wait for the answer
Share File	Share a generated file (image/zip/CSV) as a download link
Canvas Create/Update	Show markdown/code/document content in the in-app canvas panel (same title → new version)
Canvas List	List the canvas documents the agent has created

💾 Memory & files

Settings label	When to use
Read File / Write File / Edit File	Work with the agent’s working files and persistent storage
Memory Scan	List the agent’s accumulated memories
History Search	Search set-aside chunks of earlier conversation from long sessions by keyword
History Read	Pull back the body of a conversation chunk you found via search
Source Chat Read	Shared snapshot sessions only — not shown in settings. Reads the original user’s conversation up to the moment the snapshot was taken, useful when a visitor asks about decisions or facts that predate the shared session
Snapshot Transcripts Read	Dynamically provided to agents that have published at least one shared snapshot. Review the conversations external users had through your shared links to improve future versions

Tip: Agents that repeat work get smarter when you keep memory tools enabled.

💻 Code & system

Settings label	When to use
Bash	Run a one-shot shell command in an isolated sandbox (data wrangling, file processing, simple API calls). Stdout and stderr are returned separately
Computer Use	Control a GUI desktop environment and shell. Includes terminals and general GUI apps, not just browsers

⏰ Automation

Settings label	When to use
Schedule Create / List / Update / Delete	Let the agent register and manage its own runs. Supports recurring schedules (e.g. every day at 9 AM) and one-time delayed runs (e.g. run once in 30 minutes)
Task Create / Update / List	Explicitly track multi-step work with dependencies and completion state

👥 Team collaboration

Settings label	When to use
Team Agent List	Discover other agents in the team (for @mentions)
Team Agent Create	Create a new specialist agent in the team and link it on the graph (risky tool — `Approval Required` by default)
Team Agent Equip	Add tools or skills to a team-member agent. Only available to the agent that created the team (FATHER) — team members cannot equip each other
Team Chat Send / Read	Post to the team chat. `@AgentName` wakes up that agent automatically. When a mention requires a reply, the mentioned agent sends a return mention once it finishes. A thread reply (a reply to a specific mention) can wake the original sender of the message you reply to, regardless of connection direction
Team State Get / Set / List / Delete	Shared memory the whole team can read and write (separate from each agent’s private memory). Only the last agent to write a value, or the agent that created the team (FATHER), can delete it
Sub Agent Spawn	Spin up a one-off helper agent and collect the result. Only available to the agent that created the team (FATHER)

🧩 Skills

Settings label	When to use
Skill Search	Search the marketplace or the agent’s own skill library
Skill Inspect	Preview a skill’s full description file (SKILL.md) and bundled file list before installing. This step runs automatically the first time Skill Install is called
Skill Install/Activate (⚠️ approval required)	Add a marketplace skill to this agent (risky tool — `Approval Required` by default). Registered as a reference to the original without copying content; if you have previously customized the skill, your version is used
Skill Execute	Run an installed skill’s scripts in the sandbox
Skill Export (⚠️ approval required)	Package sandbox code into a reusable skill, saved as a draft for your review before publishing
Skill Feedback	Reports a defect in a skill the agent just used; for someone else’s skill it goes to the author as an improvement suggestion, and for a skill you have customized yourself it points you to fix it directly
Skill Patch	Self-edits a skill you have customized via exact-string replacement; saves a version before and after the change so you can roll back to the earlier one

🎨 Creative

Settings label	When to use
Image Generate	Text→image, reference-image edits (up to 14 reference images), multi-turn iterative refinement. Four resolution tiers (512·1K·2K·4K) and 14 aspect ratios available
Agent Set Avatar	Change the agent’s profile image via AI generation or URL. Any agent can update its own avatar; only the agent that created the team (FATHER) can update another agent’s avatar

Approval (human-in-the-loop)

Each tool has its own Auto Execute / Approval Required setting. Skill Install/Activate, Team Agent Create, and Skill Export have their per-tool approval setting turned on to Approval Required from the start, so the agent has to wait for you to approve from chat before running them. Skill Export creates a draft and shows a separate review screen before publishing.

Beyond those three, a few more tools ask for approval by default because of what they do. Share File, Sub Agent Spawn, Team Agent Equip, and Schedule Create/Update/Delete raise an approval card before running by default. HTTP Request (requests that send or change data), Computer Use (actions that change the screen), and Web Browser (actions with lasting effects like posting, paying, or deleting) also ask depending on how risky the action is. You can still tune these through their per-tool setting or your auto-approve settings. See Handling Approvals for the full breakdown.

Recommended combinations

📰 Information curation agent

Web Search + Notify User is enough.

📊 Monitoring agent

HTTP Request + Memory Scan + Write File + Schedule Create/List — track changes over time.

📝 Report writing agent

Web Search + Write File + Canvas Create/Update — research, write, and display in-app.

🔧 Data wrangling agent

Bash + Write File + Share File — process data and deliver as a download link.

Too many tools?

The more tools you enable, the longer the LLM spends reading every tool description per turn — slower responses and higher cost. Aim for 30 or fewer per agent.

If your task is so complex it needs more, split into a team. Each team-member agent can have a different tool set, and they coordinate through team chat.

Next steps

Installing Skills & Presets — Use packages where the tool combination is already tuned
Skills & the Autonomous Skill System — Save proven workflows as reusable skills. Covers how Skill Feedback and Skill Patch connect to the autonomous skill system in detail.