create_device_wtp

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

No annotations exist, so the description carries the full burden, and it does disclose a non-obvious system behavior: unreferenced wtp-profiles are pruned by FortiManager at install time, making this registration a prerequisite for settings to persist. It does not cover permissions/ADOM locking, behavior on duplicate wtp_id, or whether the call is idempotent, so it stops short of full transparency for a mutation tool.

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?

The purpose and the pruning rationale are front-loaded before the parameter list, and every line of the Args block carries information. The sole waste is the 'Returns: Creation result' line, 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 an eight-parameter mutation with no annotations, the description covers purpose, prerequisite rationale, and every argument, and a return explanation is unnecessary because an output schema exists. Remaining gaps are minor: no mention of failure modes (duplicate serial, nonexistent wtp_profile) or of the related update/delete tools an agent will need next.

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 0%, so the description must compensate, and it documents all eight parameters: device, wtp_id (explicitly identified as the serial number and table mkey), wtp_profile, name, admin with its three valid values and the 'discovered' default, location, comment, and vdom with its 'root' default. The enum values for admin are supplied only here, not in 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?

The description gives a specific verb and resource ('Register a managed FortiAP in a device's device DB') and then names the exact underlying table (wireless-controller.wtp) as the serial-to-profile mapping. That domain framing lets an agent distinguish this from the profile-management siblings such as create_device_wtp_profile or assign_vap_to_wtp_profile without opening the schema.

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 states a concrete precondition for use: a wtp-profile not referenced by any wtp entry is pruned on install, so registration is required for a profile-only setup to survive install_device_settings. That is clear 'when to use' context, but it never names alternatives (update_device_wtp, delete_device_wtp, list_device_wtps) or says when not to use it, e.g. when the AP entry already exists.

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