Zelta Daily Calorie Target

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.

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

Annotations already declare this is a safe, idempotent, non-destructive, closed-world read, so the safety profile is covered. The description adds the domain boundary against medical/pregnancy/children use, which is real value, but it never states the underlying assumption (e.g., linear loss at a fixed kcal-per-kg rate) or the return granularity (weeks vs days), which matters for a calculator whose output is only as good as its model.

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: the first front-loads the trigger scenarios, the second handles exclusions. No filler, though the three quoted example phrasings are somewhat redundant with one another and could be trimmed to two.

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 three-parameter closed-form calculator with a fully documented schema, the description covers scope, inputs, and boundaries adequately. The only meaningful gap is the absence of any statement about the estimation model or the units of the result, which an agent might want to relay to a user.

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%, with units, ranges, and the default deficit (500, max 1,000) all documented in the schema itself. The description adds nothing about parameter semantics beyond echoing '500 calorie deficit' in an example, so the baseline 3 applies.

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 conveys a specific function (estimating the duration required to lose a given amount of weight) and reinforces it with three concrete example phrasings. It does not explicitly name or differentiate itself from the sibling daily_calorie_target, but the timeline framing is distinct enough that an agent can distinguish them.

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 trigger phrasing ('how long to lose 10 kg', '85 to 75 kg how many weeks') and an explicit exclusion list (medical plans, crash diets, children, pregnancy, medication questions). Both when-to-use and when-not-to-use are stated rather than left to inference.

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