get_all_temperatures

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

No annotations are provided, so the description must disclose behavioral traits. It states the action (getting temperature and humidity) and the scope (all sensors), but does not mention potential failure modes (e.g., if some sensors are offline), response format, or any side effects. For a read-only operation, the absence of destructive hints is acceptable, but the description does not go beyond the obvious action, leaving some ambiguity for an agent about what to expect in the return.

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 a single, concise sentence that immediately states the action and scope. It front-loads the most critical information (getting readings from all sensors) without any filler. There is no redundancy, and the sentence earns its place by being both informative and efficient.

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?

Given the simplicity of the tool (one optional parameter, no output schema), the description fully covers what an agent needs to know: it retrieves temperature and humidity from all sensors in one call. The parameter is documented in the schema, and the absence of an output schema is offset by the description implying the return will contain the readings. The tool is straightforward enough that no further details are missing for correct invocation.

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 schema covers the only parameter 'unit' with a full description and enum values, giving 100% coverage. The tool description does not add any extra meaning beyond that, such as examples or clarification of the default. Since the schema already handles the parameter semantics adequately, a baseline of 3 is appropriate – the description adds no additional value.

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 uses a specific verb ('Get'), a clear resource ('temperature and humidity readings'), and a distinct scope ('from all SwitchBot temperature sensors at once'). This clearly distinguishes it from the sibling tool get_temperature (which targets a single sensor) and get_all_plugs (which targets plugs). The 'all at once' phrasing explicitly signals a batch operation, so an agent can confidently select this tool when a comprehensive sweep is needed.

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 implies batch usage ('all at once') but does not explicitly state when to prefer this tool over get_temperature or provide any exclusions or alternatives. There is no mention of use cases like 'use this when you need readings from every sensor' or 'use get_temperature for a single sensor'. The context is present but only implicit, failing to meet the bar for clear guidance.

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