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

With no annotations, the description carries the full burden and does disclose meaningful behavior: which classification system is used, that thresholds are locale-specific, that they shift for some ethnic groups, and that output is informational not diagnostic. It omits that the tool is a pure stateless calculation with no persistence, which is minor but worth noting.

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?

Two tight sentences, front-loaded with the computation and its two return elements, followed by the threshold caveat and the disclaimer. No filler or repetition.

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 a simple two-parameter calculator with no output schema, the description covers what is returned (BMI, category, healthy range) and the interpretive caveats. Slightly incomplete in that it doesn't state the return format or whether the BMI number itself is included as a field.

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% — both parameters already document units and valid ranges (kg, cm). The description only restates "weight and height" and adds no format or validation nuance beyond the schema, so the baseline of 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 gives a specific computation ("Body mass index from weight and height") and names the concrete outputs: the NHS adult category and the healthy-weight range for that height. It's clearly distinguishable from siblings like waist_ratio or weight_ideal, though it does not name any alternative explicitly.

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 supplies population context (UK/NHS thresholds, ethnic-background adjustments) and frames the output as information rather than diagnosis, which implies when the result applies. However, it never tells the agent when to prefer this over waist_ratio or weight_ideal, and gives no explicit exclusions.

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