ntp_client

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

With no annotations, the description carries full weight and does well: it discloses that fields are returned as-is ('.get'-based, nothing invented), that only `enabled` is normalized via `formatting.coerce_ros_bool`, that `servers` is deliberately left un-split, and that a device with no NTP client menu returns an empty dict rather than an error. It omits permission/read-only framing, but the error-handling and normalization disclosure is substantive.

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 core point (NTP client config/status, as-is fields, empty dict on absence) is front-loaded, but the body is padded with implementation detail, backticked internal names, and ROS6/ROS7 field enumerations that are verbose for an agent selecting a tool.

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?

An output schema exists, so the extensive return-field explanation is partly redundant, but it adds genuine convention context (no invented shape, empty dict on missing menu, sibling write handling) that the schema would not convey. Combined with the clear resource framing, the definition is complete enough to invoke 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?

Schema description coverage is 0% and the single parameter `device_name` is left unexplained in both schema and description. The description's detail is entirely about return shape, not the input parameter, so it fails to compensate for the coverage gap on the one parameter the agent must supply.

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 names the exact resource and endpoint (`/system/ntp/client`, a single-row menu) and its relationship to `container_config`, effectively telling the agent this is the NTP client read surface. It lacks a crisp leading verb ('get/return'), but the resource and read-oriented framing are unambiguous and distinguish it from the `set_ntp_servers` sibling.

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 points to `set_ntp_servers` for write behavior, implicitly establishing that this tool is the read counterpart, but never states explicitly 'use this to read NTP client config; use set_ntp_servers to modify it.' Usage is inferred rather than directed, and no exclusions or preconditions are given.

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