Tool capability versus agent authority

Capability is what a tool, API or credential can technically do. Authority is the bounded permission for this principal, task and effect. The authorized set should be no wider than the needed operation and target.

01 / The difference

Two facts that must stay separate

A cloud operations agent can call a tool exposing list_instances and terminate_instance. A production incident grants it inventory access for cluster C, not termination authority.

Established fact

Capability is what a tool, API or credential can technically do. Authority is the bounded permission for this principal, task and effect. The authorized set should be no wider than the needed operation and target.

Remaining decision

Inventory the tool’s methods and downstream effects, then map each consequential operation to its own grant and policy check. Place enforcement before the cloud API call and test a direct API route as well as the agent wrapper.

Trace the authority boundary
  1. 01Authority origin
  2. 02Task and grant
  3. 03Current decision
  4. 04Observed outcome

02 / Decision boundary

Put the check where it can stop the effect.

Inventory the tool’s methods and downstream effects, then map each consequential operation to its own grant and policy check. Place enforcement before the cloud API call and test a direct API route as well as the agent wrapper.

03 / Failure and evidence

What goes wrong, and what can be proven?

Failure mode

A tool allowlist or broad service credential is mistaken for action permission, so a legitimate inventory task can terminate a production instance.

Evidence to retain

Record the tool and method, normalized instance identifier, task grant, decision and actual cloud operation ID. Catalog visibility alone is not decision evidence.

04 / Canonical scope

Why this reference stands alone

Action-level authorization describes how to decide one verb; this comparison establishes why the surrounding tool exposure is insufficient evidence of authority.

Decision analysis

Map capability to the actual effect

A catalog is a map of possible operations. It is not a list of permitted effects. The enforcement inventory must cover each path from tool invocation to the downstream API.

list_instances
Read inventory for cluster C; allow only if the task and data scope match.
terminate_instance
Irreversible production effect; require separate grant and target check.
Direct cloud API call
Same operation; reject if the tool wrapper was the only check.

Negative test

Hide terminate_instance from tool discovery but invoke it by name, then call the cloud API directly with the agent credential. Both should still be denied without termination authority.

Primary references

Read the underlying material

Architecture discussion

Choose one consequential action and make its boundary explicit.

Request a Conversation