Skip to content

Tool Configuration

Tools help an agent do real work with less mental effort per reply. Add them when a verified scenario shows that instructions alone are not enough to keep the agent accurate, consistent, or efficient.

Tools are not the starting point. The starting point is a clear first scenario set. Add a tool only when you can point to a repeated job the agent should handle more reliably:

  • Look up stable reference material
  • Check the latest public information
  • Create a new visual from a text description
  • Hand off to a more specialized agent
  • Collect structured intake details
  • Send or fetch structured data from another system
  • Request payment before the next step continues
  • Remember stable user preferences across conversations

Agent with multiple tools configured

Start with the job, not the menu

Use this decision order:

  1. Does the agent need stable reference material that should stay consistent across conversations?

    • Use Knowledge Base for reference material the agent should search when relevant.

  2. Does the agent need the latest public information?

  3. Does the agent need to create a new visual during the conversation?

    • Use Image Generation when the user needs an illustration, concept image, or simple mockup generated from text.

  4. Does another agent already do one part of the workflow better?

  5. Do you need the user to provide information in a clean structure?

    • Use Request Form after the conversation reaches that stage.

  6. Does the agent need to send or fetch structured data from another system during the conversation?

    • Use HTTP Request only for a narrow business action, such as creating a callback lead or checking availability.

  7. Does the next step require an approved payment before it can continue?

    • Use Payment when the service, price, and next step are already approved.

  8. Do you need to remember stable user preferences across future conversations?

    • Use Memory with narrow rules about what is safe to store.

Keep the first version small

Start with the fewest tools needed for the first verified scenarios. Add the next tool only when a failed case or production pattern shows a different problem that instructions cannot solve cleanly.

The Main Tools in This Section

Tool Use it when Do not use it for
Knowledge Base The agent needs stable documents, SOPs, policies, FAQs, or reference notes Live external information
Web Search The user explicitly needs the latest public information Replacing your own product or policy knowledge
Image Generation The user needs a brand-new image, concept visual, or simple mockup generated from text Replacing approved source assets or exact final design work
Call Agent Another agent has a clearer, narrower specialty Splitting a simple task just because the tool exists
Request Form You need structured intake after the next step is clear Opening every conversation with a form
HTTP Request The agent needs to send or fetch structured data through an external API Vague “do anything” integrations without a stable contract
Payment The user must complete an approved payment before the next step continues Inventing prices, bundles, guarantees, or unapproved offers
Memory You need stable, user-confirmed preferences later Sensitive details, one-time notes, or secrets

Open the Tool Picker

In Editor, scroll to Tools and click Add Tool. The picker shows what is currently available in the workspace.

Tool picker with currently available tool types

Some options stay disabled until their prerequisites exist:

  • Knowledge Bases stays unavailable until the workspace has at least one usable knowledge folder or file.
  • Agent Tools stays unavailable until another agent exists and has a published version you can safely call.
  • Payment needs a workspace payment account before it can complete real payment requests.
  • Memory is limited to one per agent.

Write Better When to Use Instructions

Most tool mistakes are not product bugs. They come from vague invocation guidance.

Strong When to Use instructions:

  • Describe a real user request
  • Make the trigger narrow enough to avoid unnecessary tool calls
  • Explain priority when more than one source could answer

Weak:

Use this tool when needed.

Strong:

Use this knowledge base when the user asks about consultation types, routing rules, or handoff expectations that should stay consistent across conversations.

Strong:

Only use Web Search when the user explicitly asks for the latest public guidance, and prefer official or medically reviewed sources before answering.

Tool Limits and Operator Habits

  • Total tools per agent: 10
  • Maximum Call Agent tools: 5
  • Maximum Memory tools: 1
  • Tools run sequentially, so every extra tool increases the chance of a slower or less predictable path

In practice, a small, opinionated tool setup is easier to debug than a large one.

Add tools as scenarios require them

For a simple customer service agent, a practical first stack might be much smaller than the full menu:

  • Knowledge Base for the approved policy or service facts needed by the first scenarios
  • Request Form if boundary scenarios should collect structured details instead of continuing in chat
  • HTTP Request, Payment, Call Agent, or Memory only when a verified scenario needs that action

You do not need every tool on day one. Add them in the order your testing shows they are needed.

Next Steps