get_athlete_status_snapshot

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

With no annotations, the description carries the burden and does it well: it discloses that deviations are arithmetic against Garmin's baseline, that no interpretation or gating of the session is performed, and that today's data may be empty until sync. It omits auth/permission requirements, which keeps it just under 5.

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 is front-loaded in the first sentence with the metric list immediately after, and the argument note sits at the end where it belongs. The aside ('what a −22% HRV deviation means... is not') is slightly discursive but justifies the important 'no gate is applied' caveat rather than padding.

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?

An output schema exists, so return values need no explanation. Given the tool's complexity (multi-metric aggregate with derived deviations), the description covers what is returned, how deviations are derived, what it will not do, and the one real invocation pitfall (empty pre-sync day). An agent has everything needed to call it 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 0% (a bare nullable string with no description), so the description must compensate and largely does: it gives the YYYY-MM-DD format, the today default, and the non-obvious workaround of passing yesterday when a morning call is empty. It does not address timezone handling, which is the only remaining ambiguity for a date parameter.

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 verb and resource ('Get a point-in-time athlete snapshot with baseline deviations') and enumerates exactly what is inside: HRV, body battery, resting HR, readiness and sleep, each against a seven-day baseline. This distinguishes it from the single-metric siblings like get_hrv_data, get_body_battery and get_sleep_data by making clear it is a combined snapshot rather than a raw series.

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?

Gives clear contextual guidance tied to the call site: it is a point-in-time snapshot, no gate is applied, and if a morning call returns empty you should pass yesterday because the watch has not synced. It does not explicitly name alternative tools (e.g. use get_hrv_trend for trends), so it stops short of the 5 tier.

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