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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious behavior: an availability/opt-in gate that suppresses even mentioning the tool, the upstream data source (Garmin), and the fallback to the most recent round. It does not say what happens when a round has no linked health data, leaving a small gap.

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-loads the returned metrics, then the availability gate, then the default behavior — a sensible order with little waste. The metric enumeration is long but each item conveys scope; minor density cost keeps it from a 5.

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 output schema, the description compensates by listing the returned data groups and noting the round and duration are included alongside. Gating and default parameter behavior are covered; the only omission is what an agent should do when health data is unavailable for a specific round.

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, but the description adds a real resolution rule beyond the schema: with neither round_id nor date supplied it resolves to the player's last round. It does not specify precedence or interaction if both parameters are passed simultaneously.

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+resource (fetch health context for a round) and enumerates exactly what is included: sleep, recovery (HRV, Body Battery, readiness), stress, resting pulse, steps, plus the round and its duration, sourced from Garmin. It does not explicitly name the closest sibling (correlate_health_performance) or clarify how it differs, so it stops short of a 5.

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 an explicit precondition and negative guidance: only use if Badgie has it available and the player enabled it, otherwise do not offer or mention it. It also defines the default case (no round_id/date → last round). It lacks routing to alternatives such as correlate_health_performance, which would be needed for a 5.

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