create_device_interface

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

With no annotations, the description carries the full burden and does disclose the most important non-obvious behavior: the change lands in the device DB and requires a separate preview/install push to reach the FortiGate. It omits secondary traits: whether an ADOM lock is needed, whether duplicate names or vlanids error, idempotency, and permission requirements.

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-loaded with the core action and workflow routing, then a clean Args/Returns block proportionate to ten parameters. The only waste is 'Returns: Creation result,' which adds nothing given an output schema exists.

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 ten-parameter mutation tool with zero annotation coverage, the description covers action, staging-vs-live semantics, follow-up calls, and every parameter's format. An output schema means return values need no prose. Remaining gap is operational preconditions (ADOM lock, permissions, duplicate handling) that an agent would otherwise have to discover by failing.

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 0%, and the description fully compensates with an Args block that documents all ten parameters, including formats the schema does not encode: vlanid range 1-4094, ip as CIDR or 'address netmask', a concrete allowaccess example, and the role value set lan/wan/dmz/undefined.

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, and scope: create a VLAN subinterface in a device's device DB. The 'VLAN subinterface' qualifier narrows it usefully against siblings like create_device_vap, update_device_interface, and delete_device_interface, and the same sentence establishes that this writes to the staging DB rather than the live FortiGate.

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?

Explicitly places the tool in a workflow chain: read back with get_device_interface_config, then push with preview_install + install_device_settings. That tells an agent both what to do next and that this call alone does not reach the device. It stops short of naming exclusions, e.g. that modifying an existing interface requires update_device_interface rather than this create.

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