get_devices

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered without the description. The description adds only the household scoping; it says nothing about what a device record contains (name, type, connection status) despite the second example probing connectivity.

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 lines: the operation first, then the example utterances that route to it. No filler, nothing repeated from the schema or annotations.

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 zero-parameter, read-only, no-output-schema tool this is close to sufficient — an agent knows what it fetches and when. The one gap is return shape: since there's no output schema, a phrase describing the fields of a device would have closed the loop.

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; baseline 4 applies. The scope wording ("household") usefully implies the implicit filter is the authenticated household.

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?

Specific verb and resource ("List Skylight devices") with a scope qualifier ("in the household"). It does not distinguish itself from the sibling get_frame_info, which appears to cover overlapping ground (frames/devices), so an agent must infer the boundary.

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 two example questions give concrete routing signals for when to call this tool, which is more than most definitions offer. It stops short of explicit exclusions — notably it never says when to prefer get_frame_info over this.

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