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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses the >5 SD entry-error refusal, the conditional activation of the CDC projection when age and height are supplied, the cm-only input constraint with a conversion example, and the reasoning behind the locale field. That is exactly the extra behavioral context the annotations cannot provide.

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?

Dense but well front-loaded: purpose and formula first, then usage triggers, then the optional CDC mode, then the units caveat. Every sentence carries information, though the parenthetical unit example and the disclaimer rationale make it longer than strictly necessary for a single-parameter-set 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 still tells the agent what comes back (a target height with an 8.5 cm range, plus an optional CDC z-score projection with a one-SD range) and what gets refused. Nothing needed to call the tool correctly at either the required-only or optional-extended level is missing.

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 the schema already documents each parameter; the description nonetheless adds real semantics beyond it — what the sex enum does to the formula, that childHeightCm and childAgeMonths must be supplied together, and the cm-only unit requirement. It does not restate the numeric bounds, which the schema handles.

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?

Names a specific computation — expected adult height from both parents' heights via Tanner's mid-parental method — and even reproduces the formula, so the agent knows exactly what the tool returns. It is clearly separable from siblings like growth_percentile, growth_trend, and zscore_percentile, which concern a child's measured growth rather than a parental-height projection.

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 explicit trigger phrasings ('how tall will my child be', 'mid-parental height', 'child height predictor') and draws a boundary — it 'says nothing about the child's height today' — which implicitly routes current-height questions elsewhere. It stops short of naming the sibling tools that should be used instead, so it is clear context without full alternative routing.

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