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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuinely useful scope disclosure: it is a pure numeric conversion and deliberately excludes clinical interpretation, which prevents misuse as an assessment tool.

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?

Two sentences, zero filler, with the conversion direction and the exclusivity rule front-loaded and the scope caveat last. Every sentence carries distinct information.

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 3-param, no-output-schema tool, the description covers direction, exclusivity, and scope. Minor gap: it does not mention that the response may include a physician-written disclaimer/clinician note keyed by locale, which is an observable output the caller should expect.

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, but the description adds a constraint the schema does not encode: exactly one of zScore/percentile must be supplied (no oneOf/anyOf in the schema). The locale disclaimer/clinician-note behavior is left to the schema description rather than echoed here.

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 bidirectional verb+resource (z-score ↔ percentile on the normal curve) and scopes it as the growth-chart relationship, which cleanly separates it from siblings like growth_percentile or birth_size_percentile that compute percentiles from measurements. An agent can distinguish it without opening the schema.

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 a clear invocation rule ('Pass exactly one of zScore or percentile') and an implicit when-not: it converts numbers but 'does not say what it means for a child', steering clinical interpretation to other tools. It never names a specific alternative sibling, so it stops short of a 5.

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