pt_create_device

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the mutation profile is covered. The description adds only the opaque phrase 'native IPC' and does not explain the non-idempotent consequence — e.g. what happens on a duplicate name, whether the device count/topology changes visibly, or whether an open simulated network is required. With annotations present the bar is lower, but almost nothing beyond them is contributed.

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?

Two short sentences, front-loaded with the action and resource, with no padding. The bilingual duplication roughly doubles the length but is a formatting convention rather than filler, and the content is tight.

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?

There is no output schema, so the description should say what the call returns (e.g. a device identifier or updated topology state) — it does not. For a mutation tool that requires four parameters including workspace coordinates, omitting the prerequisite of an open network and the post-call effect leaves a significant gap.

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%, so all five parameters are documented in the schema, and this establishes a baseline of 3. The description adds only that the device is 'named' and restates the kind categories the enum already lists (and even misses multilayer_switch). No extra semantics about coordinate units or model defaults are offered beyond the schema.

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: adding (creating) a named PC, router or switch. This clearly separates it from sibling operations like pt_connect_devices, pt_list_devices, and pt_configure_ios. It stops short of naming an alternative, and it omits the 'multilayer_switch' kind that the enum allows, but the core purpose 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?

There is no guidance on when to use this versus pt_new_network/pt_open_network, nor any stated prerequisite that a workspace must already exist and be open. The word 'native IPC' hints at an execution environment but does not tell the agent the conditions for a successful call. The agent must infer the workflow entirely from sibling names.

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