Create private network

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

Adds extensive behavior beyond annotations: asynchronous creation, polling via operation and get_private_network until port_intent_ready, graph-stage nuance, no automatic attachment, explicit networking:read/manage requirements, quota/2FA enforcement, and in_progress versus failure semantics. It also aligns with the idempotentHint by stressing preservation of the original idempotency key and never auto-retrying on transport uncertainty.

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 purpose, subnet rules, async behavior, and auth/approval constraints efficiently for such a complex operation. However, the polling and idempotency guidance is repeated in multiple places, so the description is longer and less tightly structured than it could be.

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?

Given a complex open-world, idempotent, asynchronous creation tool with no output schema and only partial parameter description coverage, the description covers the critical operational concerns: auth scope, approval, subnet allocation, async polling, reason_code handling, idempotent recovery, and the fact that creation does not attach or purchase connectivity. It gives an agent enough to call and monitor the tool correctly.

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?

With 50% schema description coverage, the description adds important semantics for subnet and subnet_prefix_length: uniqueness across the platform, 100.64.0.0/10 range, omission behavior, default /26, capability-based sizing, alignment rules, and subnet_in_use conflict. It does not explain default_policy or add much beyond the schema for some other nested settings, so it is strong but not fully comprehensive.

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: creating an approved private network for existing services when no suitable owned network exists. It also distinguishes the operation from attachment or public-address purchase by saying creation does not itself attach a server or buy a public address.

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 a clear condition for use: when no suitable owned network exists, and clarifies that a false order-availability result alone does not block this route. It also says to read current capabilities and owned resource state first and obtain approval, though it does not name the exact alternative sibling tool for checking existing networks.

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