Create network VPN peer

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

With annotations already declaring readOnlyHint=false, idempotentHint=true and openWorldHint=true, the description still adds a great deal: the accepted-but-pending nature of the operation, the polling contract on in_progress with next_check_seconds, how to interpret reason_kind waiting vs failure, permission/ownership/2FA enforcement by the backend, and the no-automatic-retry rule on transport uncertainty. It also discloses that the gateway generates the WireGuard key and that private key material must stay out of MCP.

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?

Front-loads the core action and key-material constraint in the first three sentences, then handles lifecycle, permissions and recovery. Dense but information-bearing throughout; the polling/reason_code passage is long and could be tightened, which keeps it from a 5.

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 complex async mutation with no output schema, it covers the operation lifecycle, idempotency recovery, and interpretation of status fields well enough to call and poll correctly. It leaves the concrete shape of the returned operation/resource slightly implicit, but no serious gap remains for a caller.

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 60%, and the description compensates meaningfully: it clarifies that grants is a 0-16 list of owned grant-candidate IPv4 addresses with split-tunnel/full-tunnel semantics, and that reveal_public_key is a one-time X25519 public key whose private half must remain external. gateway_id, idempotencyKey and reveal_public_key already carry schema descriptions, so this is additive rather than essential.

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 ('Add a device' as a network VPN peer) plus the key mechanic (externally generated one-time public reveal key), which separates it from revoke_network_vpn_peer, set_network_vpn_peer_grants and take_network_vpn_peer_config. It doesn't explicitly name any sibling, so an agent must infer the boundary, but the action is unambiguous.

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 concrete usage conditions: 0-16 owned grant-candidate IPs, split-tunnel requires at least one, full-tunnel may be empty. It also states prerequisites ('Read current capabilities and owned resource state first; obtain approval for the exact change') and required scopes. It stops short of naming alternative tools for adjacent operations, so 4 not 5.

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