get_vo2max_history

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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, but the description still adds substantive behavior: one Garmin request per year of range, result caching, required local auth via garmin-owl-auth, no automatic retry on Garmin failures, and an explicit prompt-injection caution about treating events as data. Only gap is no note on result shape or what a failed/partial fetch looks like, but an output schema exists.

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-loaded with the core purpose and the disambiguation before the operational details, and each paragraph covers a distinct concern (scope, data caveats, events, auth/safety). It is on the long side and the sport sentence earns no place since the parameter is absent from the schema.

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 two-parameter read tool with an output schema and safety annotations already declared, the description covers everything the agent needs: what the points mean, how to interpret empty days, the caching/request-cost model, auth prerequisites, and failure behavior. The dangling 'sport' reference is the only real blemish.

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 start_date/end_date semantics are already fully documented in the schema, making 3 the baseline. The description does add real meaning about data density ('one point per day Garmin updated them') and the gap interpretation, plus the one-year-per-request constraint. However, it discusses a 'sport' parameter (generic vs. cycling) that does not exist in the input schema, which risks an agent passing an unsupported argument.

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 and resource ('Get Garmin's VO2 max estimates'), the granularity ('one point per day Garmin updated them'), the horizon ('up to three years'), and the extra field ('fitness age'). It explicitly names the two siblings it is not (get_training_load for today's status, get_activities for per-activity vo2_max), so an agent can route without opening a schema.

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 a positive trigger ('Use for VO2 max or fitness-age trends') and explicit alternatives with the conditions that select them (today's status vs. per-activity values). It also warns against a specific misuse ('do not read them as missing data') and explains what the returned events field is for.

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