get_training_summary

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered (the description's '(read-only)' merely repeats it). Beyond that, the description adds genuine behavioral context: how numeric custom fields are aggregated by units/meaning, that device loads are summed apart from Intervals.icu load, and that missing values are skipped rather than counted as 0.

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-loads the core purpose and the alternative-tool routing, and every sentence carries information. However, the long run-on enumerations of aggregated metrics are dense and slightly harder to parse than necessary.

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?

There is no output schema, so the description carries the full return-value burden, and it does so thoroughly: it enumerates the per-group and total metrics, zone/sport/gear splits, fitness metrics (CTL/ATL/form/ramp), and the custom-field aggregation rules. Complete for a tool of this complexity.

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 100%, so the schema already documents all 8 parameters. The description still adds meaning by explaining the grouping options and, importantly, the numeric custom-field aggregation semantics and detail_level output implications, which go beyond the enum labels.

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 resource (training totals) with explicit scope (grouped by ISO week, month, sport, gear, or total) and clearly distinguishes itself from the sibling get_weekly_summary by naming that per-week view belongs to the other tool. An agent can select this without opening the 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 clear usage context (training totals of a period, grouped) and routes the per-week single-call case to get_weekly_summary, plus points to the method guide via get_guide. It stops short of exhaustive when/when-not guidance against the many analysis siblings, but the key alternative is named.

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