Heart rate variability

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

Annotations already declare this as a safe, idempotent read operation. The description adds useful behavioral context beyond that by explaining that the response changes from a single-night summary with readings to aggregated nightly averages, weekly averages, baseline, and status when an end_date is supplied.

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?

The description is a single dense sentence that front-loads the default single-night behavior and then explains the range behavior. There is no filler and every clause conveys a distinct mode or output detail.

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 read-only tool with no output schema, the description explains the two primary modes and what data is returned in each. It leaves some ambiguity, such as what happens if only start_date is provided, but the core behavior is sufficiently clear for an agent to invoke the tool correctly.

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 the baseline is 3. The description earns a 4 by adding semantic meaning beyond the schema: the presence of end_date switches the tool from single-night retrieval to a range aggregation mode with different returned fields.

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 identifies the resource as overnight HRV and clearly describes the two data shapes: single-night summary/readings versus range-based nightly averages and status. It is specific enough that an agent can distinguish it from sibling metric tools like get_heart_rate or get_sleep, even though it does not explicitly name those siblings.

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 a clear conditional: without end_date you get one night, and with end_date you get per-day range summaries. This is actionable guidance for selecting between the two modes. It does not explicitly state when to prefer this over any sibling, but siblings cover different metrics, so the main usage decision is the date-range mode, which is covered.

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