Home overview

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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine payload context: which categories appear and the notable behavior that unavailable entities skip the ones expected to be off. It does not say how results are grouped/ordered or how large the response can get, which would complete the picture.

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 dense sentence with the key framing ('One call snapshot of the whole home') front-loaded, followed by an inventory of contents where each clause carries information. It is list-heavy but not padded; a brief structural grouping of the items would have made it easier to scan.

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?

With no output schema and a broad aggregate scope, the description effectively doubles as a return-contents summary, covering version, domain counts, presence, locks/alarms, covers, climate, lights, unavailable entities, batteries, updates, automations, integration problems and repairs. For a one-optional-parameter read tool whose safety profile is fully annotated, that is close to sufficient; the missing piece is guidance on when this is preferable to the more targeted siblings.

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 100% – the single 'sample' parameter already documents its meaning, default of 10, and 1-50 range. The description does not mention sampling at all, so it adds no meaning beyond the schema; baseline 3 applies.

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?

States a specific verb+resource ('One call snapshot of the whole home') and enumerates the included sections precisely, so an agent knows this is a single aggregate status call rather than an entity-level query. It never names a sibling (e.g. get_dashboard, find_problems, get_system_health) to draw the boundary, so differentiation is implicit.

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 phrase 'One call snapshot' implies the intended use – a fast whole-home status pass instead of many targeted calls – but there is no explicit when-to-use/when-not guidance, no mention of preferring find_problems or get_entity_details for deeper dives, and no stated preconditions.

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