Zelta BMI for Indians

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

Annotations already declare readOnlyHint/idempotent/non-destructive, so safety is covered. The description adds genuinely useful behavior beyond them: the response shows the Asian-Indian category alongside the WHO one, which tells the agent what the output contains. No permissions or side effects are a concern for a pure calculation.

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?

Front-loaded with 'Use this when', followed by examples and a compact do-not-use clause; the examples earn their place by mirroring likely user phrasings. Slightly long as one run-on sentence, 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 no output schema, the description usefully states that both Asian-Indian and WHO categories are shown, and it bounds eligibility (adults, non-pregnancy). Combined with the fully documented schema, an agent has what it needs to invoke it correctly.

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 four height/weight parameters are already documented with types and bounds. The description only loosely reinforces units through its example phrasings ('72 kg', '5 ft 6'), adding little beyond the schema, which makes the baseline 3 correct.

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 states a specific resource (BMI) and scope (adults, weight category interpretation, Asian-Indian vs WHO cutoffs), which is enough for an agent to identify it. It does not explicitly differentiate itself from the sibling healthy_weight_range, so it falls short of the top mark.

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 gives concrete triggering examples ('BMI for 72 kg 165 cm', 'am I overweight at 5 ft 6 and 70 kg') and explicit exclusions: children/teens under 18, pregnancy, diagnosis, treatment and medication questions. The only gap is that no alternative tool (healthy_weight_range) is named for those cases.

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

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behaviour, so the safety profile is covered. The description adds domain context beyond annotations: the result is derived from Asian-Indian and WHO cutoffs, so the agent knows the interpretation rules differ from a generic BMI lookup. It does not, however, mention alternative input-unit combinations or rounding/output format.

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 description is front-loaded with the trigger situation, then examples, then the computation source, then exclusions — a logical order. The example list is slightly verbose for three cases, but each example illustrates a distinct input style, so it earns its place.

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 one-input, no-output-schema lookup tool with full annotation coverage, the description gives the trigger, the cutoff basis, and exclusions. The remaining gap is guidance on which of the three optional height parameters to supply, which matters because all are unrequired.

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 each height parameter is already documented in the schema, so baseline is 3. All three params are optional with no required field, yet the description never explains that height_cm and height_ft/height_in are alternative ways to express the same measurement or how to choose between them.

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 states a specific verb and resource — it returns a BMI-based healthy weight range for an adult height — and immediately grounds it with three concrete user phrasings. It is distinguishable from the sibling bmi_check because it returns a weight range under specific population cutoff tables rather than a single BMI score.

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 gives explicit inclusion criteria ('when an adult asks what weight is normal or ideal') and a clear exclusion list ('not for children, pregnancy, athletes judged on muscle, or diagnosis'). This is the when/when-not guidance that most definitions omit entirely.

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