Set network VPN site options

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: states the change is recorded at once but carried on the VPN's next generation (possibly after a planned recreate), documents the 503 vpn_site_routing_unavailable condition, the required scopes, backend ownership/feature/2FA enforcement, and detailed polling semantics (in_progress vs reason_kind, preserving reason_code, no automatic retry). This is far richer than the readOnly/openWorld/idempotent/destructive hints alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Long and dense, but front-loaded with the core true/false semantics before operational detail, and each sentence carries distinct information (permissions, error code, polling, retry). Minor cost: the polling/retry material is generic operation handling that inflates length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and thin annotations, the description carries the full burden and does so: it covers the effect of the setting, apply timing, required scopes, failure conditions, and how to confirm completion via get_network_vpn_gateway and router routes_update lines.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: gateway_id is documented but hub_and_spoke is a bare boolean. The description compensates by fully explaining the boolean's meaning (true = offices reach each other through the VPN, each still limited to its granted servers; false/default = isolated), which is the key semantic the schema omits.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Switch hub-and-spoke for the locations (offices) connected to this VPN,' and immediately clarifies what true vs false means. It is clearly distinguishable from siblings like get_network_vpn_gateway (which it explicitly routes to for polling) and set_network_vpn_site_alert.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear when-to-use conditions (hub_and_spoke=true for mutual reachability, false for isolation) plus prerequisites: read current capabilities and owned resource state first, obtain approval for the exact change, and requires explicit networking:read/networking:manage. No sibling alternative is named for making this change, so it stops just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.