known_devices

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description does add a genuine behavioral fact beyond the annotations — the result spans offline devices, not just currently reachable ones — but says nothing about ordering, pagination, or freshness of the registry data.

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 tight sentences with the scope statement front-loaded before the filter list; nothing redundant. The opening is slightly impressionistic ("what the registry remembers") rather than crisp, which costs a point.

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 shape is handled elsewhere, and the description correctly focuses on scope plus filtering. What remains missing is match behavior for the filters and any result-size/pagination expectation, minor gaps for a simple discovery tool.

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%, so the description must carry parameter meaning; it does name all three filters (owner, tag, online state), matching the three parameters. However it adds no matching semantics — exact vs substring for tag/owner, or how "online state" maps to the online_only boolean — so compensation is only partial.

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 phrase "everything the registry remembers, online or not" conveys the resource (registered devices, including offline ones) but never names the list/query verb explicitly, so the purpose is implied rather than stated. It hints at a distinction from live-scan siblings like scan_network, but does not name or contrast with list_devices or device_history.

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?

"Filter by owner, tag, or online state" describes capability, not when to choose this tool. There is no condition selecting it over the many siblings (list_devices, scan_network, who_is_new, device_history), no exclusions, and no prerequisites.

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