get_recovery

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

With no annotations provided, the description carries the disclosure burden, and it succeeds by revealing that the tool explicitly reports missing data with reasons. This is valuable behavioral context beyond a plain metric fetch. It does not mention authentication, rate limits, or data source freshness, but the presence of an output schema reduces the need to describe return structure.

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?

The description is a single, dense sentence that names the resource, the operation, the involved metrics, and the absence-handling behavior. It has zero filler and front-loads the core aggregation purpose, making it highly scannable for an agent.

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?

Given the output schema exists to document return values, the description covers the essential selection context: what data is aggregated and how missing data is handled. The only minor gap is date format/semantics, but with a single optional parameter and default null, the tool remains fully invocable. This is slightly better than the minimum viable definition.

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 must compensate for the single 'date' parameter. While the description doesn't explicitly mention the parameter, the tool's name and action make it clear that an optional date selects the recovery window. With only one optional parameter and a clear default of null, the semantics are reasonably inferable.

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 verb ('Combine') and resource ('Garmin sleep, HRV, Body Battery, stress, RHR, readiness'), making the tool's purpose clear. It does not explicitly differentiate it from sibling tools like get_daily_summary or get_training_readiness, but the aggregation framing sets it apart from the individual metric tools.

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 'states why any is absent' implies this tool is a comprehensive recovery aggregator, useful when a consolidated view is wanted instead of querying each metric separately. It doesn't explicitly list exclusions or alternatives, but the 'combine' wording gives enough context for an agent to select it over getting single-metric siblings.

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