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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real substance beyond that: the discrete verdict vocabulary, the baseline warm-up thresholds, and the important caveat that this is Daash's own computation rather than Garmin's official readiness score. It stops short of stating behavior for missing/partial data or future dates beyond the not_enough_data verdict.

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?

Purpose and the metric list are front-loaded, and the caveats follow in a logical order; the Args block is compact. The opening sentence is dense and run-on (five clauses plus parentheticals), which slightly slows parsing but contains no 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 single-optional-parameter read tool with an output schema, this covers everything an agent needs: what data feeds the check, what the verdict values mean, when the verdict is unavailable, and that the score is derived rather than sourced from Garmin. Return-value detail is correctly left to the output schema.

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 0%, so the description carries the full burden and does it well: explicit YYYY-MM-DD format, the 'today'/'yesterday' keywords, the '-1' offset form, and the default to today. That is more than the bare string|null schema could ever convey.

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?

Names a specific resource ('a recovery check for a day') and enumerates exactly what it aggregates: last night's sleep, overnight HRV, resting heart rate, Body Battery and last week's training. The four possible verdicts (ready_for_hard, fine_with_care, go_easy, not_enough_data) make it unmistakable that this is the readiness tool and not get_sleep_data or get_daily_summary.

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?

Implies a daily-recovery use case and gives data-sufficiency conditions ('no call until a week of nights gives an HRV baseline; an early one until about three weeks'), which is useful. It never names or excludes a sibling though, so an agent must infer on its own whether to reach for get_daily_summary or get_sleep_data instead.

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