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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description goes well beyond them by enumerating exclusions (auxiliary loads, transmission losses, demand/capacity charges, green-power premia, carbon cost) and stating the tariff must come from the caller. This is exactly the extra context an agent needs to interpret the number correctly.

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 labeled Purpose/Guidelines/Limits/Ex structure front-loads the formula and keeps the exclusions scannable. It is a dense single block with some run-on clauses, but nearly every clause carries distinct information.

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?

An output schema exists, so return formatting need not be described, and the description still covers scope limits, defaulting behavior, required inputs, and a worked example. Nothing material for correct invocation is missing.

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 baseline is 3, but the description adds real meaning: the fallback-and-cite behavior of pue, the 8760-hour default, and the energy-only return when electricity_price is absent. language and response_format are left entirely to the schema, which is acceptable.

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+resource (calculate compute energy cost) and immediately exposes the formula it implements: IT load x PUE x hours (x tariff). This distinguishes it cleanly from siblings like get_pue_benchmarks (data lookup) and calculate_cbam_cost (different cost domain).

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 Guidelines sentence is explicit about what must be supplied (it_power_kw), what is optional, and the conditional behavior of each optional field (missing pue -> cited benchmark; missing electricity_price -> energy only). It does not name an alternative tool to use instead, but the conditions that select this tool are unambiguous.

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