Anthropic tool-use authority

Check the selected tool and normalized arguments in the client dispatcher before calling the customer API.

01 / Principal and identity

Who acts, and what can the platform identify?

A model requests a tool; the client application is the executor and accountable caller.

The application can associate the request with its signed-in user and case.

Trace the proposed action
  1. 01Originating task
  2. 02Agent or workload
  3. 03A customer-support tool changes a shipping address.
  4. 04Observed effect

02 / Action-time control

Where can an unauthorized effect be stopped?

Check the selected tool and normalized arguments in the client dispatcher before calling the customer API.

A case grant may allow a read but require customer verification for an address write.

SubjectVerified caller and task
RequestOperation, target and values
OutcomeDecision, attempt and state

Delegation constraint

Tool selection is a proposal, not delegated permission from the user.

03 / Worked denial

Test a request outside the grant.

The model selects change_address for a different customer after reading a ticket note.

Adversarial verification

Return a tool_use block for a customer ID outside the signed-in user’s case. The client dispatcher should return a denial tool_result while the customer API records no address mutation.

04 / Review and responsibility

What should the audit trail prove?

Message/tool-use ID, case, verified customer, requested values, denial and unchanged record.

This architecture applies to client-executed tools; server-executed capabilities require their own boundary.

Platform primary source

Check the current execution model

Architecture discussion

Map one consequential action in your environment.

Request a Conversation