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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower. The description adds that results are a time series and gives the underlying REST endpoint, but discloses nothing about rate limits, auth scope, or response shape.

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?

Three tight clauses: what it returns, how to parameterize it, and the underlying REST path. The key calling rule is front-loaded with zero 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?

For a 3-param read tool with full schema coverage and a readOnlyHint, this is nearly complete — the agent knows the resource, the inputs, and the two mutual-exclusive modes. Only the absence of any note on returned granularity/pagination keeps it from a 5.

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 schema already documents date, the period enum, its default, and that endDate overrides period. The description restates the period/endDate exclusivity rather than adding format or edge-case detail.

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 specific resource (heart-rate time series) and enumerates the concrete contents (resting HR, time in each HR zone). It is also clearly distinguishable from the closest sibling, fitbit_hrv, which covers variability rather than HR zones.

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?

Explicitly disambiguates the two calling modes — 'single date + period, OR a date + endDate range' — which is exactly the decision an agent must make before invoking. It stops short of naming an alternative tool or when-not-to-use, but the parameter-mode guidance is concrete.

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