training_summary

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

Annotations already cover read-only/idempotent/non-destructive, so the description rightly spends its words elsewhere: null semantics ('fields Garmin did not record say "not recorded"; never treat them as zero') is valuable guidance an agent cannot get from structured fields, and the informational/not-medical-advice disclaimer sets framing. No contradictions with annotations.

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?

Three tight sentences, front-loaded with what is returned before the use case and caveats. The stray 'I1.' prefix is noise, and the metric list is long but each item is genuinely a returned field.

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 return values need no explanation; the description still covers scope, granularity, null handling and intent framing. Nothing an agent needs to call this correctly is missing.

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/end/group_by are already fully documented in the schema. The description only echoes the grouping choice and the 366-day window, adding no syntax or edge-case detail beyond the schema — baseline 3 is appropriate.

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?

Names the resource and the scope precisely ('training totals over up to 366 days, by week or month') and enumerates the exact metrics returned (sessions, hours, hours/week, evening sessions, aerobic effect, per-sport breakdown). The use-case cue "'how much did I train' questions" separates it from siblings like trend, compare_periods and weekly_review without needing 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 a clear trigger condition (aggregate training-volume questions) plus hard bounds (max 366 days, week/month granularity). It stops short of naming alternatives or exclusions — e.g. when to prefer compare_periods or weekly_review for the same style of question is left to inference.

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