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

Annotations already establish that this is a safe, idempotent, closed-world read (readOnlyHint, idempotentHint, openWorldHint=false), lowering the burden. The description adds useful domain constants (4 kcal/g for protein and carbs, 9 kcal/g for fat) but says nothing about the return structure, units handling, or that all 11 inputs are optional and defaulted.

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 compact sentences plus a reference URL; no filler. It is slightly front-loaded with a nutrient constant rather than the primary action, but the tool's function is still apparent by the second clause.

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 11-parameter calculator with no output schema and no required fields, the description covers the intent but not the mechanics: it never explains that body metrics drive an internally computed calorie target (the text implies the user supplies one), nor how the three-split output is shaped. Adequate but with real gaps.

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%, so the baseline is 3. The description adds some meaning — the kcal-per-gram model behind the conversion and the three goal modes — but leaves the metric/imperial duality (cm vs ft/inch, kg vs lb) and the role of `units`, `activity`, and `diet` entirely to the schema.

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 names a concrete transformation (a Mifflin–St Jeor calorie target → daily macro grams) and scopes it to fat loss, maintenance or gain across three diet styles, so the agent knows exactly what the tool produces. It does not, however, position itself against the crowded sibling set (protein_calculator, bmr_calculator, tdee_calculator), which share the same nutrition domain.

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 only implied: mentioning 'your Mifflin–St Jeor calorie target' hints that a calorie target is the input context, and the goal/split language maps to the goal and diet enums. There is no explicit when-to-use vs when-not, and no guidance on choosing this over protein_calculator or tdee_calculator.

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