iaas_create_network

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

Annotations already disclose non-read-only, non-destructive, non-idempotent and open-world behavior, so the description only needs to add operational context. It does add one useful trait: the network is tied to the machine's lifecycle and must be explicitly destroyed to free resources, warning about orphaned cost-bearing resources. It omits auth requirements, what happens on partial failure, and whether creation is asynchronous.

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?

Four short lines: purpose, mechanism, lifecycle caution, and HTTP path. It is front-loaded with the action and contains no filler. The redundant "Create network" header line is the only minor waste.

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?

The schema fully documents the request body and annotations cover safety, but with no output schema the description never says what a create returns (e.g., a request tracker / task id from an asynchronous provision). For a provisioning call with nested constraint semantics, that missing return/progress information is a real gap, though the lifecycle warning is a compensating strength.

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 description coverage is 100% and even nested objects (constraints, tags, customProperties) are documented inline, so the schema carries almost all the semantic weight. The description only echoes this by saying the network is provisioned "based on the passed in constraints," without adding format or defaults beyond what the schema states.

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?

The description states a specific verb and resource ("Create network" / "Provision a new network"), which is easy to distinguish from read siblings like iaas_get_network(s) or iaas_delete_network. It does not explicitly disambiguate against the closely-named iaas_create_network_profile, but the object being created (a network, from constraints) 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?

It gives no guidance on when to call this versus related tools such as iaas_create_network_profile, iaas_allocate_network_ips_by_user, or the deployment-level creation endpoints. The only conditional statement — "should be destroyed after the machine is destroyed" — is a lifecycle note, not a cue for choosing this tool.

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