Get trend

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

Annotations cover only the safety profile (readOnly/idempotent/openWorld), and the description adds substantial behavior the annotations cannot: automatic aggregation switching (daily up to two months, weekly up to a year, monthly beyond), a hard two-year range cap, per-metric Garmin request cost (steps ~14 requests/year vs one for weight), and the exact semantics of 'change' (last whole period's average minus the first, short periods excluded).

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 the core outcome, then density-packed supporting detail. The per-metric request counts are useful for latency expectations rather than filler. It is long for a description, but nearly every clause carries operational information, so only minor trimming is possible.

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?

Although an output schema exists, the description still explains the summary fields (days_with_data vs periods_with_data for VO2 max, average/min/max, first/last day, change definition), which prevents misreading. With four parameters, a hard range limit, and metric-dependent granularity all covered, nothing an agent needs to invoke correctly is missing.

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. The description exceeds that by glossing metric meaning — hrv, readiness is the morning score, stress is the day's average, body_battery is the day's high, vo2max is running vs vo2max_cycling — and by explaining that aggregation is inferred from the range when omitted, which changes the shape of the result.

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 specific job — how one metric moved over a range, returning average, extremes and change — over a named enumerable set of metrics. It clearly differentiates from single-metric siblings (get_steps, get_hrv) and from get_day_summary by scope. An agent can select it without opening the schema.

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?

Explicit routing: 'For one day use get_day_summary or that metric's own tool; for every weigh-in rather than one a day, list_weigh_ins.' It also states range limits (two years) and implies when to prefer this aggregate view. Both the when-to-use and the when-not-to-use cases are covered with named alternatives.

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