scan_lan_ips

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

With no annotations supplied, the description carries the full burden and does disclose two non-obvious traits: an approximate ~6 s blocking listen window (latency), and that it persists state ('save any light IP'), i.e. it mutates stored addresses, not just reads. It still omits what happens if nothing is found, what is returned, and any network/permission prerequisites, which keeps it below a 5.

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 behavior and its time cost, then the redundancy caveat. Nothing is padded, though the phrasing 'any light IP that changed' is imprecise rather than economical.

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 a parameterless, no-output-schema, no-annotation tool the description covers the essentials — what it does, how long it takes, and that it is usually automatic — but leaves the outcome underspecified: whether addresses are only updated or also added, whether results are reported, and what a caller should do afterwards.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the empty schema is fully consistent with the no-argument call described. Baseline 4 applies for a parameterless tool.

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 mechanism ('Listen for Tuya broadcasts') and the effect ('save any light IP that changed'), so the agent can infer LAN discovery of lights. However, 'IP that changed' is ambiguous — changed relative to what baseline? — and it never plainly states that this scans the local network for light addresses, which is what the name suggests. No sibling tool covers discovery, so it is distinguishable by default rather than by explicit contrast.

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 second sentence ('Commands already do this automatically when a light is unreachable') gives a real usage signal: this is normally redundant and only needed as a manual fallback. But it never states the positive trigger — e.g. 'call this when a light you expect is missing from list_lights' — and names no alternative tool for troubleshooting.

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