workout_series

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses auto-downsampling, the hard limit on returned points ('never returns more than max_points points'), the reporting of downsampled/source_points/returned_points/method plus summary stats, and numeric t offsets in seconds. It also explains the normalization behavior and the effect of reference_max_hr, providing rich context beyond a simple API call.

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 three sentences long, front-loaded with the primary purpose, and every sentence carries essential information. There is no redundancy or filler. It covers behavior, constraints, and the key usage caveat about reference_max_hr efficiently.

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 tool's moderate complexity, lack of output schema, and 5 parameters, the description is remarkably complete. It explains the return format (points with t offsets, summary stats), the downsampling behavior, the max_points constraint, and the cross-activity normalization caveat. No significant gaps are evident for an agent to select and invoke the tool 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 description coverage is 60%, and the description adds meaningful semantics for key parameters: reference_max_hr ('used to normalize time_in_zone... pass a consistent value when comparing zone distributions'), max_points ('Hard cap on returned points (server-enforced)' is in schema, but description reinforces 'never returns more than max_points'), and resolution ('increased automatically when needed to stay within max_points' is in schema, but description adds 'auto-downsampled'). It does not elaborate on workout_id or metric beyond schema, but those are straightforward. The description adds value beyond the schema for the most nuanced parameters.

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 clearly states the tool's purpose: 'Get an agent-safe, auto-downsampled time series for a workout metric.' It identifies a specific verb (get), resource (time series for workout metric), and unique differentiators (agent-safe, auto-downsampled, contract version). It also distinguishes from sibling tools by focusing on the downsampling behavior and cross-activity normalization, which is not mentioned for query_heart_rate or query_metric_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?

The description provides clear context for when to use the tool, especially regarding reference_max_hr: 'For cross-activity comparison of time_in_zone, pass reference_max_hr... otherwise each activity is normalized to its own max and zone distributions are not comparable across activities.' It implies usage for workout metric time series, but does not explicitly name alternatives or state when not to use the tool. This is a clear context without explicit exclusions, aligning with a score of 4.

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