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

Annotations already cover safety (readOnlyHint, idempotentHint, closed-world), so the description's job is supplementary — and it delivers: it discloses the return content (litres, gallons, and the formula itself). The worked example '30 × 20 × 10 cm box holds exactly 6 litres' also implicitly documents the default behaviour. It does not mention rounding/precision, which keeps it out of the top band.

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 with no filler, though the lead sentence is a worked example rather than the purpose, so the core capability is not strictly front-loaded. The trailing web-page URL is promotional padding that does not help an agent invoke the tool.

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 names the return values (litres, gallons, formula), which covers the biggest gap. However, for a 5-parameter, 6-shape tool with zero required parameters, it leaves the shape-dependent meaning of x/y/z and the interpretation of the 'none' unit option 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 100%, so the baseline is 3, and the description adds little: it lists shapes (already an enum) and uses 'cm' in the example (already the unit default). It does not explain how x/y/z map to radius/height for sphere, cylinder, cone or pyramid, which is the one thing the generic 'Length/Width/Height' schema labels leave ambiguous.

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 ('Get the volume of a cube, box, cylinder, sphere, cone or pyramid') and enumerates the supported shapes, which separates it from area_calculator, circle_calculator and triangle_calculator. It never explicitly names a sibling or rules one out (e.g. concrete_calculator, which also produces volumes), so it falls short of the top tier.

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?

Usage is only implied by the purpose statement: an agent can infer 'use this to compute solid volume', but there is no when-to-use framing, no prerequisites, and no alternative tool named for adjacent needs (area, surface area, material volume).

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