Sync from Garmin

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

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is partly covered. The description still adds real value beyond them by disclosing that metrics get recomputed (explaining why it is flagged as non-read-only) and that a call typically takes 10-30 seconds, which matters for timeouts and retry planning.

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?

Two short sentences, zero filler. The data scope comes first and the latency warning second, so both key facts are front-loaded.

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?

With no parameters and no output schema, the main things an agent needs are scope, side effects, and duration, all of which are present. It could go further by noting auth/failure behavior or whether repeated calls are safe, though the idempotency annotation already covers the latter.

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?

The tool takes no parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No misleading parameter hints are introduced.

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 pairs a specific verb ("Fetch new data") with a named source (Garmin) and enumerates the record types covered (activities, sleep, HRV, wellness, weigh-ins), plus the recompute step. That scope instantly separates it from the read-only siblings like get_today or list_activities.

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?

The phrase "Fetch new data" implies the tool should be run before consuming the reader siblings when data may be stale, but this is never stated explicitly and no sibling is named or excluded. An agent must infer the sequencing from context rather than from the text.

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