search_activities

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

Annotations already cover read-only and open-world safety, yet the description adds real behavioral value: it returns exactly one page, a subtype in activityType yields a 400, an unknown sortBy or requiredFields name silently returns NO activities rather than an error, and Garmin rejects a bounding box wider than 50 km. These silent-empty-result traps are the sort of thing an agent cannot infer from annotations or schema.

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?

The opening sentence is well front-loaded, but the rest is a sprawling run-on enumeration of every filter that repeats the schema, and the text is truncated mid-word ('bound…'), signaling an incomplete definition that was not curated to fit its purpose.

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?

For a search tool with no output schema, nothing is said about what a returned activity record looks like or whether paging metadata (total counts, next offset) comes back. Combined with the truncation and the missing sibling differentiation, an agent cannot fully predict the response or confirm this is the right list tool.

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 single top-level `filters` parameter is undocumented, but the nested schema already describes every sub-filter in detail (units, inclusive bounds, parent/subtype rules, enum values), so the schema carries most of the burden. The description's parameter content—a list of filter names with units—largely duplicates rather than extends the schema.

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 concrete verb+resource (search activities) and a precise scope: one page of results filtered by text/type/date/metrics. However, it never distinguishes itself from the many sibling list tools (get_activities, get_activities_by_date, get_activities_for_date, count_activities), and calling itself 'the `getActivities` endpoint' actively blurs the line with the `get_activities` sibling.

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 implied by the enumerated filters, and useful operational rules are given (activityType must be a PARENT key, subtype → 400, use activitySubType; boundingBox must be ≤50 km). But there is no explicit when-to-use/when-not statement and no routing to alternatives such as get_activities_by_date or count_activities.

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