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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered; the description adds real behavioral context beyond that: it depends on an external climate dataset (NASA POWER), it degrades to a summary output above 1,000 m², and it only supports a rectangular block footprint. The added guidance to answer with returned numbers rather than a guess is a meaningful behavioral instruction. It does not disclose latency, failure modes for unsupported locations, or default assumptions when optional parameters are omitted.

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 content is front-loaded with the outcome (heat loss/gain, load figures, monthly energy, plant selection) followed by geometry, use categories, and size limits. It is dense and list-like but every sentence carries information. A minor cost is the telegraphic phrasing ('use: residential, office, retail…') which reads as shorthand rather than prose.

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 no output schema, the description usefully enumerates what comes back — design loads in kW and W/m², monthly energy, and plant selection — plus the size threshold at which detail is truncated. For an 8-parameter computational tool with 0% schema documentation, the remaining gap is input semantics: two optional parameters and all units/defaults are left unexplained.

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 0% across 8 parameters, so the description must carry the load. It does explain the geometry contract (length_m × width_m × storeys) and enumerates the valid values of use, and lat/lng are implicitly framed as the building's location for climate lookup. But window_ratio and storey_height_m — both materially affecting an energy calculation — are never mentioned, and no units or defaults are given for any parameter.

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: real heat loss and heat gain calculation for a building, driven by NASA POWER climate data for its location, returning design heating/cooling loads (kW, W/m²), monthly energy, and plant selection. It also states the geometric model assumed (rectangular block: length_m × width_m × storeys), which sharply bounds what the tool does. It never explicitly contrasts itself with siblings like wai_design_building or wai_datacenter_energy, so it stops short of full sibling differentiation.

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?

There is an implicit usage constraint — detailed results only up to 1,000 m² gross floor area, with larger buildings falling back to a summary — and an explicit instruction to report the returned numbers rather than a pre-call estimate. However, no guidance is given on when to prefer this tool over siblings such as wai_design_building or wai_datacenter_energy, and no preconditions (permissions, required climate coverage) are stated.

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