listActivities

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

With no annotations, the description carries the full burden and does well on the read path: it discloses result ordering, the shape of the compact summary, that certain fields appear only "when Garmin has them" (conditional presence), and the date format. It omits pagination/continuation behavior beyond the limit, and says nothing about authentication, rate limits, or error behavior for large or unbounded limits.

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?

Purpose and ordering are front-loaded, followed by return-content detail, so the reader gets the essential information immediately. The middle is a long semicolon-chained field list that is dense to read, but given the absence of an output schema those items largely earn their place.

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?

With six optional parameters all covered by the schema and no output schema, the description's main remaining duty is explaining return content, which it does thoroughly, including conditional fields and the raw alternative. Only minor gaps remain (pagination beyond limit, auth expectations), which do not block correct invocation.

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 all six parameters (raw, limit, names, startDate, endDate, activityType) are already documented in the schema. The description only restates the raw flag and the yyyy-MM-dd format, adding no filtering semantics or defaults beyond what the schema provides, so the baseline of 3 applies.

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 ("List the user's Garmin activities"), plus ordering ("most recent first") and output form ("compact summary" versus raw JSON). It enumerates the summary fields and the raw escape hatch, which makes it distinguishable from the single-activity sibling getActivity without opening either 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?

Usage is only implied: an agent infers this is for enumerating multiple activities and that raw=true should be used when full Garmin JSON is needed. There is no explicit when-to-use versus getActivity/getActivityLaps guidance, and no statement of exclusions or prerequisites.

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