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

Annotations already declare the tool read-only and non-destructive, so the description adds meaningful behavioral context beyond them: it uses current Voltcast curves, allows optional user tariff inputs, and discloses that carbon/balanced modes rely on a trailing historical production-mix profile rather than a forward forecast. The explicit 'no emissions-reduction claim' caveat is high-value transparency that prevents misuse.

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 two sentences with no filler. The core purpose and primary inputs are front-loaded, and the important methodological caveat is placed second, making the tool's limits immediately visible.

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?

The description covers the tool's purpose, input mode, and key limitation clearly enough for an agent to select and invoke it confidently, especially with schema descriptions for count, tariff, objective, and duration_minutes. It does not describe the exact output structure, but the verb 'rank' plus the absence of an output schema makes the intended result reasonably inferable.

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 57%, so the description is not required to fully compensate for the schema, but it also does not explain the less-documented parameters like zone, to, and from. It adds some value by mentioning optional variable tariff inputs and the experimental objective modes, but it mostly mirrors schema descriptions rather than enriching them.

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 names a specific verb and resource: 'Rank household action windows by cost' using 'current Voltcast curves' and optional user-supplied tariff inputs. It also distinguishes itself from sibling tools by explicitly flagging that carbon/balanced modes are not forward carbon forecasts, which separates it from get_carbon and get_forecast.

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 clear usage context: use this tool to rank windows by cost or via experimental carbon/balanced modes, with optional tariff inputs. It includes an important exclusion by warning that the carbon/balanced modes are not forward carbon forecasts and support no emissions-reduction claim, though it does not explicitly name alternative sibling tools.

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