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

Annotations already establish readOnly, non-destructive, and closed-world, and the description adds genuinely new context: the output is an educational estimate with no guarantee or offer semantics, and no PII should be supplied. It stops short of saying what the returned figures look like (annual? per-period?), which would matter for a calculation tool with no output schema.

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?

Three short sentences, each doing distinct work: use condition, exclusion boundary, and a safety instruction. The use condition is front-loaded and nothing is repeated from the schema.

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 an eight-parameter, read-only calculation tool with rich schema descriptions and no output schema, the description covers purpose, boundaries, and input safety well. It is slightly incomplete in that it never indicates the form of the result (e.g., annual bill saving in AUD) or that unspecified rates default rather than being required.

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% and the schema already documents defaults (peak sun hours 4.2, performance ratio 0.80, self-consumption 0.30) and constraints. The description only restates three of the eight parameters at a high level, adding no unit, range, or default meaning beyond the schema, so the baseline 3 applies.

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 the required inputs (daily kWh, tariffs, system size) and the output nature ('classroom energy-bill arithmetic'), which separates it from a quoting or credit tool. It does not name or contrast with any sibling such as compare_scenarios, so an agent still has to infer which of the nine siblings is the right entry point for multi-scenario work.

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?

It gives a clear use condition ('when you have daily kWh, tariffs, and a system size') plus explicit exclusions ('not a quote, a savings guarantee, or a credit offer') and a data-handling instruction ('do not send an account or identity number'). The one gap is that it never routes the agent to an alternative tool when the situation is comparative or decision-oriented.

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