Article

Tools

Tools are visible capabilities with explicit policy, approval, and execution rules. They are not hidden side effects.

Tools

Tools are explicit capabilities exposed to the runtime.

In Decubed, a tool is not just a model hint. It has a durable description, a live registration, permission requirements, and an execution result that must be normalized back into the thread.

Two Layers

Decubed keeps tool behavior split across two layers:

  1. the durable definition that the model can see
  2. the live executable registration that actually performs the action

That split makes it possible to expose tools clearly without confusing prompt-visible description with executable privilege.

Permission And Approval Flow

Tool execution follows a canonical order:

  1. the tool is requested
  2. the runtime resolves required permissions
  3. policy is evaluated
  4. approval is requested when needed
  5. the tool runs only if allowed
  6. output is normalized into the thread

Approval is not the same thing as permission. Both surfaces matter and both should stay visible.

Durable Policy

Durable tool policy lives in the environment, not in a hidden provider session.

That lets the product answer concrete questions like:

  • which tools are enabled in this workspace
  • which tools are available to this agent
  • which actions require approval
  • which permissions are currently denied

Why This Matters

AI products often collapse tools into invisible side effects.

Decubed keeps them visible so the workspace can show:

  • what the model tried to do
  • why it was allowed or blocked
  • how long it ran
  • what came back

Examples

The tool surface can include:

  • file inspection
  • browser tasks
  • calendar reads
  • reminders
  • contacts
  • local shell or runtime actions

Different tools may have different policy and approval requirements, but they still pass through the same runtime shape.

Related Reading