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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds real value by disclosing the return shape (percentile range buckets from 24 months) and that it 'Returns no interpretation'. It does not, however, state behavior under 24 months or any error/edge-case handling.

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 the core computation and efficiently packed with domain detail across five tight sentences. There is minor redundancy in restating the CDC split ('the split the CDC advises') and the final sentence is a fragment, but overall it earns its length.

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 carries the return-value burden and does so for the 24+ month case, explicitly noting the percentile buckets and the absence of interpretation. What a sub-24-month caller receives (e.g. z-score only) is left implicit, a small gap for a clinical 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%, so baseline is 3; the description adds meaning by tying ageMonths to the WHO/CDC threshold and explaining that childhood BMI must be read against age and sex. It reinforces param semantics rather than merely restating 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?

States a specific verb and resource ('Computes BMI from weight and height, then places it on the BMI-for-age chart') and scopes it precisely by age band. An agent can distinguish this from generic growth_percentile or ponderal_index without opening any schema, because the output and chart basis are named.

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?

Gives clear contextual guidance: WHO under 24 months, CDC 2000 from 24 to 240 months, and explicitly warns not to read childhood BMI against adult 18.5–25 bands. It stops short of naming sibling tools (e.g. growth_percentile, zscore_percentile) or stating when those would be preferred.

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