garmin_training_load

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

With no annotations, the description carries the full behavioral burden; it usefully explains the semantics of each computed metric (42-day vs 7-day EWMA, TSB = CTL - ATL), which is genuine added context. It does not disclose permissions, cost, computation windows relative to 'now', or caching behavior, so the mutation/IO profile is only partially covered.

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 purpose sentence followed by a tight bulleted list; no filler prose. Slight redundancy in enumerating returns, since an output schema already exists and covers them.

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?

An output schema exists, so the return-value list is largely duplicative, while the description omits the more valuable missing piece: how this differs from its many training-related siblings. Complete enough to call, but not complete for selection in a crowded tool space.

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?

The tool takes zero parameters, so the schema has nothing to document and the baseline is 4. The description correctly implies the computation is derived from stored activity history with no caller-supplied filters.

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 ('compute ... training periodization metrics from activity history') and names the metric family (CTL/ATL/TSB), which distinguishes it reasonably from generic status tools. However, it never explicitly contrasts with close siblings like garmin_training_status or garmin_load_focus, so a borderline case remains.

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?

No when-to-use guidance at all, and no mention of alternatives despite several overlapping siblings (garmin_training_status, garmin_load_focus, garmin_trends). The agent must infer the selection condition from the metric names alone.

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