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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safe, deterministic read profile is covered. The description adds genuine domain behavior beyond that: it is scoped to adults 18-80 and explicitly out of scope for medical/clinical populations. It does not say what values come back (TDEE vs target calories vs macros), which is the remaining gap.

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, front-loaded with the use case and a dense set of example triggers, followed immediately by the exclusion list. No filler, and the ordering puts routing information before caveats.

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 an 8-parameter calculator with no output schema, the scope, boundaries and trigger conditions are all covered, and 100% schema coverage handles the inputs. The one omission is a hint about the returned values (e.g. target calories plus maintenance figure), which an agent would otherwise have to discover by calling.

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 enums are documented in-schema, so the baseline is 3. The worked examples ('30 year old woman 70 kg 160 cm', 'deficit for 0.5 kg a week') illustrate which inputs drive the result but add no syntax or unit semantics beyond what the schema already states.

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?

The description states a concrete purpose through trigger phrasing and worked examples ('how many calories should I eat to lose weight', 'TDEE calculator', 'calorie deficit for 0.5 kg a week'), so an agent knows this computes a daily calorie target. It does not differentiate from the sibling weight_loss_timeline, which is the only thing keeping it from a 5.

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?

It gives explicit when-to-use triggers (adults asking about intake for loss or maintenance) and explicit when-not-to-use exclusions (children, pregnancy/breastfeeding, eating disorders, medical diets, medication questions). Nothing is left to inference.

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