activity_streams

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

With no annotations, the description carries the full burden. It usefully discloses that the original FIT file is fetched and cached locally, plus what the response contains, but says nothing about cost/latency of the download, response size for long activities, or error behavior when a FIT file is missing.

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 short sentences with no filler: what is returned, the downsampling behavior, the analysis use cases, and the caching note. Front-loaded and efficient, though the caching remark could have been folded in more tightly.

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?

There is no output schema, and the description does a reasonable job of enumerating the return payload (session values, laps, streams with channel list), which is the main thing an agent needs. Units, stream field naming, and volume for long activities remain unspecified but are secondary.

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 coverage is 0% — both parameters are bare titles. The description does explain the key one, resolution_seconds, as the downsampling interval and implies what gets downsampled, but gives no default, units, or valid range, and never mentions activity_id at all.

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 concrete action: it loads the original FIT file and returns session values, all laps, and a downsampled stream with named channels (HR, pace/speed, power, cadence, altitude). That is enough to separate it from summary-level siblings like daily_summaries or activity_details, though no sibling is named explicitly.

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?

"Ideal für Intervall-, Pacing-, Drift- und Zonen-Analysen" gives real use-case guidance for picking this over a plain activity summary. However, it never says when NOT to use it, nor points to the concrete alternative (e.g. activity_details for a lighter call), so the agent must infer the boundary itself.

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