Set VPN server access

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

Goes well beyond the annotations (destructive/idempotent/openWorld) by disclosing auth scopes (networking:read vs networking:manage), backend enforcement (ownership, feature availability, 2FA locks), and detailed async polling semantics including reason_kind/reason_code interpretation. It also states the critical caveat that an accepted operation is pending, not proof of firewall delivery or connectivity.

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?

Purpose is front-loaded and the operational detail is dense but every block is substantive. There is mild redundancy – the point that an accepted operation is not proof of connectivity is made twice ('do not treat the setting operation as proof of firewall delivery' and 'An accepted operation is pending, not proof of connectivity').

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?

For a destructive, open-world, asynchronous mutation with no output schema, the description covers the full lifecycle an agent needs: capability preconditions, required reads, auth scopes, async polling with next_check_seconds and reason codes, and idempotent recovery. Nothing essential is missing.

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 67%: gateway_id and idempotencyKey are documented in the schema, but the mode enum carries no schema description. The description names the two values and frames mode as controlling the VPN's access to attached servers, but does not explain what 'accept' vs 'groups_only' actually means, so it only partially compensates.

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 and resource ('Set VPN server access', choosing 'accept or groups_only for the VPN's access to attached servers'), which is clearly distinct from neighboring tools like set_network_vpn_peer_grants or set_network_default_security_policy. It doesn't explicitly name a sibling it must not be confused with, but the resource scope is specific enough for correct selection.

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 context: act only 'when this capability is available', read the gateway network and security policy first, and obtain approval for the exact change. It stops short of naming alternative tools or stating when-not to use this one, but the preconditions are explicit.

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