get_recent_activities

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'normalized sport-aware summary fields', which gives some insight into the response structure, but does not disclose important aspects like whether this is a read-only operation, how pagination works (though limit/days params exist), or any rate limits. The absence of side-effect warnings is a gap since mutation tools would need such disclosure, but here the tool appears read-only; still, the description does not explicitly state that.

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 sentence, front-loaded with the core purpose ('Recent Garmin activities') and adds a meaningful qualifier about the output fields. It is efficient and avoids redundancy. However, it is arguably too sparse, sacrificing essential details for brevity, but the conciseness itself is well-executed.

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 has an output schema, so the description need not explain return values, but it should still provide enough context for an agent to know when to invoke it. The description lacks usage guidelines and parameter semantics, and while the output schema may cover the return shape, the description does not connect the tool's purpose to the available parameters. The low parameter coverage and missing guidance make it incomplete for a tool with only two optional 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?

Schema description coverage is 0%, and the description does not mention the 'days' or 'limit' parameters at all. The description only says 'recent', which implies a time window but does not explain how the 'days' parameter controls that window or what 'limit' does. With no parameter documentation in either the schema or description, the agent has no way to know how to set these parameters correctly.

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 clearly identifies that the tool returns recent Garmin activities, and the phrase 'normalized sport-aware summary fields' adds specificity about the output format. It distinguishes from sibling tools like get_activity_detail (which likely returns a single activity's detail) by implying a summary-level list. However, it lacks an explicit verb like 'retrieve' or 'list', and the differentiation from siblings is only implicit.

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 provides no guidance on when to use this tool versus alternatives such as get_activity_detail or get_training_load. It does not mention any prerequisites, exclusions, or scenarios where this tool is preferred. The only hint is 'recent', which is vague. Without explicit usage context, an agent may not know if this is the right tool for a given query.

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