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

Annotations already establish read-only, idempotent, closed-world, non-destructive behavior, so the bar is lower. The description still adds real context: it enumerates the returned quantities (percentile, z-score, 3rd–97th percentile cutoffs at that age), names the LMS table provenance, and explicitly states 'Returns no interpretation' — a meaningful scope boundary for a clinical tool. It stops short of out-of-range or failure behavior.

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?

Three compact sentences, front-loaded with what the tool does before the return payload and the no-interpretation caveat. The percentile-value enumeration is slightly listy but earns its place by disclosing return content in the absence of an output schema.

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?

There is no output schema, so the description carries the return-value burden and does so by naming percentile, z-score, and reference cutoffs. Combined with the annotations covering safety and the fully documented schema, an agent has enough to call it correctly; only out-of-range/error behavior and the bmi_percentile overlap remain unaddressed.

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% and four enums are fully annotated, so all parameter meaning already lives in the schema; baseline is 3. The description reinforces the WHO/CDC parameter choice in prose ('WHO or CDC growth reference chart') but adds no unit, format, or edge-case detail beyond what the schema says.

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-equivalent (compute placement) and resource (one child measurement against WHO/CDC references), and the phrase 'one measurement' implicitly separates it from trend tools. It never names a sibling, so the overlap with bmi_percentile and zscore_percentile is left for the agent to resolve. Clear purpose, but no explicit sibling differentiation.

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?

Usage is implied by the inputs (age + metric + value = one-shot percentile lookup), and the WHO vs CDC framing hints at when each standard applies. However, nothing states when to prefer this tool over the sibling bmi_percentile despite this tool accepting metric='bmi', nor when growth_trend or growth_reference_range is the better pick. Implied usage only.

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