get_frame_info

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The "get" verb implies a non-destructive read, and the setup/debugging framing adds light context, but the description does not disclose return format, failure behavior, or auth requirements. Adequate for a simple info lookup but adds little beyond what the name already implies.

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?

The description is compact and well-structured: a one-sentence purpose, a usage framing sentence, and a bulleted list of example queries. Every sentence earns its place, and the examples are genuinely actionable for an agent. No wasted words or vague filler.

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 0-parameter, no-output-schema tool, the description covers the essentials: what it retrieves and when to invoke it, reinforced by concrete example questions. It could marginally mention what the response contains (e.g., frame ID, household settings), but the provided examples already name the key output (frame ID), making the description reasonably complete for this simple 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?

The tool has zero parameters, so the baseline is 4 per the rubric. There is nothing for the description to explain regarding parameters; the schema trivially covers 100% and the description correctly does not invent any. No deduction is warranted since there is no parameter surface requiring elaboration.

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 states a specific verb+resource: "Get Skylight household/frame information." This clearly distinguishes the tool from siblings like get_devices and get_family_members — it retrieves the household/frame identity-level data, not device or member lists. It is not a tautology of the name and is unambiguous about scope.

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 gives concrete usage context: "Useful for setup verification and debugging," plus two literal example user utterances ("Show Skylight household info", "What's my frame ID?"). This helps an agent match intents to the tool. It doesn't explicitly state when NOT to use it or name alternatives, but for a 0-param info tool the guidance is sufficiently clear.

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