watch

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

Annotations only declare read-only/non-destructive safety; the description adds substantial non-obvious behavior: poll rate (once per second), output shape (one CSV row per second with watts/volts), and critically that 'the call takes as long as the duration asked for' — a blocking-duration characteristic an agent must know before invoking. This is genuine value beyond annotations.

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?

Four sentences, front-loaded with the core capability and resolution, then output, then use case, then the duration caveat. Efficient with little waste, though the output and use-case sentences could be tightened.

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 3-param, no-output-schema read tool, the description covers resolution, output format, blocking duration, and intent. It omits error/limit handling and interaction with the 'channels' default, but is largely complete 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?

Schema coverage is 100%, so the schema already documents pf, seconds, and channels thoroughly. The description nonetheless reinforces the time semantics ('given number of seconds', 1s resolution) and the watts-vs-volts per input type, adding light value without redundancy.

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 (live view/polling) and resource (device inputs over a duration), and crisply differentiates from the stored-log sibling 'query' by noting it is 'finer than the stored log' at 1-second resolution. An agent can distinguish it from snapshot or energy_by_interval without opening a schema.

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?

Gives a clear use case ('catch an appliance being switched on or off right now') that tells the agent when this tool is appropriate. It does not explicitly name when to avoid it or which sibling to prefer for historical data, so it stops short of the top band.

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