get_activity_fit_data

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It clearly states that the tool downloads and parses a FIT file, exposes parsed metrics, auto-fetches body weight from Garmin, and may return very large payloads when include_records is true. It also discloses hardware compatibility constraints and defines shift-quality classifications, preventing misinterpretation of returned values.

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 long but front-loaded with a clear purpose and every bullet identifies a distinct data category. The shift-quality definitions and compatibility notes are useful rather than filler. Minor redundancy exists: the 'full per-second time series' behavior appears both in the bulleted returns list and again in Args, so a small amount of trimming was possible.

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?

For a complex, annotation-free tool, this description is nearly complete: it covers purpose, return categories, parameter meanings, prerequisites, and a payload warning. It does not mention whether the downloaded FIT file is stored locally or whether set_fit_download_dir must be configured first, and it implies a cycling activity without explicitly saying so. These are minor gaps given the output schema exists and sibling tools hint at download-directory behavior.

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 Args section is essential. It explains activity_id as 'Garmin activity ID' and include_records as an optional per-second time series with a clear volume warning, adding meaning beyond the bare schema. It could go slightly further by describing acceptable ID forms, but it sufficiently compensates for the missing schema descriptions.

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 opening sentence uses a specific verb and resource: 'Download and parse FIT file for an activity to expose advanced cycling data.' It then clearly distinguishes the tool from the standard REST API by enumerating the advanced metrics returned. This makes its purpose and differentiation from siblings like get_activity or download_activity_file immediately clear.

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 explicitly frames the tool as the way to obtain data 'not available through the standard REST API' and provides hardware prerequisites for DI2 and cycling dynamics data. It also gives practical guidance on the include_records flag by warning about data volume. However, it does not name sibling alternatives or state when NOT to use this tool, such as when only a raw FIT file is needed.

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