scan_network_devices

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds real value on top of that: it explicitly states that no network configuration is changed, that no device gets selected or connected, and it bounds the timeout at 2-15 seconds. It still says nothing about failure behavior, such as what happens with an invalid or non-local IP, or about network traffic or broadcast effects.

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?

A single compact sentence: it front-loads what the tool does, lists the returned fields, then states the negative guarantees and the timeout constraint. There is no filler and nothing is repeated from structured fields.

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 return values need no explanation, and the annotations cover the safety profile; against that, the definition is nearly complete. The remaining gap is operational: it does not say where to obtain a valid interface_ip, or how errors are surfaced, both of which matter for an open-world discovery call.

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 has to carry the parameter meaning, and it partially does: it says the interface must be a local NIC address and that the timeout ranges from 2 to 15 seconds, which the schema does not state. However, it never gives the expected interface_ip format (IPv4 literal versus an adapter name) or says whether values from list_network_interfaces are expected, and the timeout bounds do not say what happens when they are exceeded.

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 a specific verb and protocol (DCP Identify) on a specific resource (a designated local NIC) and states exactly what comes back: device IP/MAC/name only. It also distinguishes this from the sibling selection tools by declaring that it does not select or connect devices.

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?

The description makes clear when to use it (a scan-only lookup on a local interface), and rules out the adjacent actions by saying it does not modify configuration, select, or connect. It never explicitly points to list_network_interfaces for finding a valid interface_ip or to select_network_device for follow-up, so routing guidance is implied rather than stated.

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