set_activity_typeChange the category of an existing Garmin activity by providing its activity ID and a type key such as running, cycling, swimming, or walking.
Change the type/category of an existing activity.
| Name | Required | Description | Default |
|---|---|---|---|
| typeId | No | Optional activity type ID | |
| typeKey | Yes | Activity type key: running, cycling, swimming, walking, etc. (required) | |
| activityId | Yes | The unique activity identifier (required) |
Changes observed during successful MCP inspections.
v4.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations include destructiveHint: true, which already signals that this tool modifies data. The description adds minimal behavioral context beyond that—it says 'change' which aligns with the destructive hint. It doesn't disclose any side effects, reversibility, or permission requirements. Since annotations already cover the destructive nature, the description adds little extra value, but it doesn't contradict the 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?
The description is a single, concise sentence that clearly states the purpose. It's front-loaded and efficient, with no wasted words. It could potentially add a bit more context, but for a simple mutation tool, this level of conciseness is appropriate.
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?
Given the tool's simplicity (3 params, no output schema, no nested objects), the description is adequate but not complete. It doesn't mention that typeKey is the primary way to specify the type, nor does it clarify the optional typeId parameter. It also doesn't reference related tools like get_activity_types for discovering valid type keys. The annotations provide some context (destructiveHint), but the description could be more helpful by explaining the relationship between the two type parameters.
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 schema description coverage is 100%, so all three parameters (activityId, typeKey, typeId) are described in the schema. The description itself doesn't add any additional parameter semantics beyond what the schema provides. The schema already explains that typeKey is required and typeId is optional, and the description doesn't clarify the relationship between typeKey and typeId (e.g., which takes precedence). Baseline 3 is appropriate given high schema coverage.
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 'Change the type/category of an existing activity' clearly states the verb (change) and resource (activity type/category), and it distinguishes from siblings like set_activity_name and set_activity_privacy. However, it doesn't explicitly mention that it modifies an existing activity, which is implied by 'existing' but could be more explicit about the mutation aspect.
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 implies usage for changing an activity's type, but it doesn't provide explicit guidance on when to use this tool versus alternatives like set_activity_name or set_activity_privacy. It also doesn't mention any prerequisites or context (e.g., needing to fetch activity types first). The sibling list includes get_activity_types, which could be a prerequisite, but the description doesn't reference it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.