Skip to main content

Visibility vs Operability

Visibility means an agent can discover an operation exists. Operability means an agent can invoke it.

An operation can be:

  • Visible and operable — Discoverable and executable
  • Visible but not operable — Discoverable but gated (e.g., requires approval)
  • Not visible — Hidden from the agent entirely

This distinction prevents agents from assuming that discovery implies permission.

Declaring Operability​

<button
  axag-intent="user.delete"
  axag-entity="user"
  axag-action-type="delete"
  axag-visible="true"
  axag-operable="false"
  axag-operability-reason="Requires admin approval"
  axag-approval-required="true"
  axag-approval-roles='["admin"]'
>
  Delete User
</button>

This tells the agent: you can see this operation exists, but you cannot execute it without admin approval.

How the Runtime Decides​

@web-axag/webmcp computes operability from the page rather than from the attributes: an action whose element is disabled, hidden, inert, aria-disabled or detached is withdrawn from the agent's tool list, and offered again when the element comes back. So a button your UI disables is already not operable, without annotating it.

The visibility attributes are declarations for readers and for your own code; the 1.1 manifest doesn't carry them. To keep an action off an agent's list deliberately, use the binding's enabled option in React, Vue or Angular, and let the server refuse it too.

Next Steps​