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

Annotations already cover read-only/idempotent/non-destructive, so the bar is lower. The description adds genuinely useful clinical context beyond them: the output is a 'statistical classification and not a diagnosis', and it flags that the locale-selected disclaimer is a physician-authored safety text that should not be paraphrased. It doesn't discuss determinism or rate limits, but for a pure computation tool this is solid added value.

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-loads the core definition and each following sentence adds distinct value (scope distinction, concrete example, output/nature of result). Slightly long, but no sentence is 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 carries the return-value burden and does so: it names percentile, z-score, and SGA/AGA/LGA category, plus the interpretive caveat. Combined with 100%-covered inputs, an agent has everything needed to call and interpret the 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 description coverage is 100% and the descriptions are rich (grams vs cm, obstetric vs corrected age, locale rationale), so the schema does the heavy lifting. The prose adds no additional parameter syntax or constraints beyond what the schema already states; baseline 3 is appropriate.

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 (birth measurement on the Olsen 2010 intrauterine curves) and a specific input dimension (completed weeks of pregnancy), and explicitly differentiates itself from the growth charts: 'not how a child grows over time, but how big they were on the day they were born'. This lets an agent separate it from growth_percentile/growth_trend siblings without opening a 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 clear context for when this tool applies versus the growth charts, including a worked contrast (2.2 kg at 34 weeks vs 40 weeks). It does not explicitly name the sibling tool (e.g. growth_percentile) it should be chosen over, so the alternative is implied rather than routed by name.

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