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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, closed-world), so the bar is lower. The description adds genuine context beyond them: it names the competing formulas, notes that supplying resting HR switches to the Karvonen method, and shows a concrete worked value, which tells the agent the result is deterministic bpm ranges.

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-loaded with a concrete example followed by the method options, then a reference URL — no filler. The second sentence carries three distinct ideas (formula choice, personalisation, HR-reserve), which is dense but still readable.

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 must signal the return value, and 'all five training zones' plus the numeric example does that. For a three-parameter, zero-required calculator the remaining gap is minor — it doesn't specify whether personalisation changes all five zones or only the boundaries.

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 real meaning the schema lacks: it maps the opaque enum 'fox' to '220 − age' and explains that the optional resting parameter activates the Karvonen/heart-rate-reserve method. It does not, however, state the behavior when resting is supplied (replaces vs. augments the age-based zones).

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 concrete verb+resource: 'Get all five training zones from your age', and the opening example ('Zone 2 for a 30-year-old is 114–133 bpm') makes the output shape immediately unambiguous. It is clearly a fitness/HR tool distinct from the many finance/conversion siblings, but it never explicitly distinguishes itself from adjacent health calculators like bmr_calculator or tdee_calculator.

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 explains the three computational paths ('220 − age or Tanaka, or personalise them with resting HR'), which is really guidance for choosing among parameters rather than when to pick this tool over a sibling. No statement of when-not-to-use or of a preferred alternative, so usage is only implied.

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