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

Annotations already declare readOnly, idempotent and non-destructive behavior, yet the description still adds real value: it discloses the underlying model ('same model as the calculator in Sky Solar's guide'), the geographic applicability ('near Munich'), and that the output is 'an illustration, not a quote' — a caveat about result reliability that annotations cannot convey.

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?

Purpose is front-loaded in the first clause and the closing line 'An illustration, not a quote' is a dense, useful caveat. The input list in the first sentence is long but each item earns its place; minor tightening possible but no filler.

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?

With annotations covering the safety profile and full param coverage in the schema, the remaining burden is scope, model provenance, and result reliability — all addressed. The one gap is that, with no output schema, the shape of the returned sizing result (kWp figure, module count, assumptions) is never described.

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 100%, so each of the six parameters is already fully documented, and the baseline is 3. The description restates the same inputs (consumption, heat pump, car, orientation, roof area) and flags roofM2 as 'optionally', but adds no bounds, units, or defaults beyond what the schema gives.

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 and resource ('how big a rooftop solar system should be') plus the exact inputs that drive the answer, so the agent knows this is a sizing/estimation tool rather than a lookup like battery_savings or find_subsidies. No sibling is named explicitly, but no sibling overlaps the sizing job, so ambiguity is low.

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?

'For a household near Munich' and the consumption-plus-planned-load framing give implied usage context. However, there is no explicit when-to-use / when-not guidance and no pointer to related tools (e.g. battery_savings for storage sizing, consultation_link for a real quote), so the routing decision is left to inference.

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