Training history by week

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context: it returns aggregated weekly rows plus overall totals in a single call, and it is scoped to 'recent weeks' with a default of 12 weeks. It does not disclose pagination or exact date-range behavior, but the output schema likely covers the return shape. The description adds value beyond annotations without contradicting them.

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 sentences with no filler. The first sentence states the resource and purpose, the second details the output shape, and the third gives usage guidance. Every sentence earns its place, and the key scoping information ('recent weeks', 'single call') is front-loaded.

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?

The tool is a read-only summary with an output schema, so the description does not need to explain return values in detail. It covers the main use case, the output granularity, and the alternative approach. The only minor gap is that it does not explicitly describe the activity_type parameter's effect or allowed values, but the default and the running-specific output fields make this inferable. For a read-only aggregation tool, this is nearly complete.

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 description must compensate. It does partially: it explains the 'weeks' concept by saying 'recent weeks' and 'one row per week', and it implies activity_type by saying 'running' is the default and the output includes distance/sessions/longest run/average pace. However, it does not explicitly explain the activity_type parameter or its allowed values, and it does not state the range of the weeks parameter. Still, the description gives enough context to infer both parameters' roles.

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 description states a specific verb ('Returns'), a clear resource ('weekly training volume over recent weeks'), and the exact output shape (one row per week with distance, sessions, longest run, average pace, plus overall totals). It also distinguishes itself from sibling tools by framing the output as the input for writing a plan, which separates it from garmin_activities, garmin_activities_by_date, and garmin_last_activity.

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 says when to use it: 'Use this before designing a plan rather than fetching activities one range at a time.' This names the alternative pattern (fetching activities range by range) and gives a clear condition for choosing this tool. It also implies the tool is a high-level summary, not a detailed activity fetch.

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