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

With readOnlyHint=true and idempotentHint=true annotations already covering the safety profile, the description adds meaningful behavioral context: it restricts the tool to adults, confirms it computes rather than looks up values, and documents the output fields and formula. It does not mention auth or rate limits, but those are not critical for a pure calculation API, and it does not contradict the annotations.

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?

Although the description is longer than many tool definitions, every block earns its place: usage, exclusions, computation summary, inputs, outputs, formula, REST fallback, and docs link. It is front-loaded with the most decision-critical information (when to use and when not to use) and then systematically provides call details. No word is wasted.

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 straightforward calculation tool with only two required parameters and an existing output schema, the description covers every facet an agent needs: precise use cases, age restriction, alternatives, input examples, output field names, the underlying formula, and even a REST fallback endpoint. There is no ambiguity about when or how to invoke the tool.

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 provides full descriptions, units, examples, and value bounds for weight_kg and height_cm. The description's 'Inputs' line only repeats the parameter names and units, adding no meaningful semantic depth. The complete JSON examples provide mild format guidance, but this does not elevate the score above the baseline for full schema coverage.

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 opens with a specific verb and resource list: 'an adult's BMI, its WHO/CDC weight category, or the weight range that corresponds to a normal BMI'. It clearly differentiates itself from siblings like calculate_bmr and calculate_tdee by explicitly naming them as alternatives for calorie needs, and it excludes children under 20. An agent can immediately tell what this tool does and what it is not for.

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?

The description contains an explicit 'Use this when...' phrase followed by a 'Do not use this when...' section that lists concrete exclusions (under-20 age, body-fat percentage, calorie needs) and names the sibling tools to use instead. This is the gold standard for usage guidance; nothing 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.