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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds real behavioral context beyond that: skill scores only appear 'where synced,' and some data (On target, stats to work on) exists for 'newer sessions' while focus-score and median data spans older ones, warning the agent that results can be sparse or partial. It stops short of describing ordering or volume of returned sessions.

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?

Two sentences, front-loaded with the core purpose followed by routing guidance; every listed item maps to actual returned content. The return enumeration is dense but each clause earns its place, with only mild redundancy in the phrase 'per session' / 'of each focus session.'

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 no output schema, the description carries the burden of explaining return values and does so thoroughly enough to set expectations. The one material gap is the 'days' window and what happens with limited history, which matters for a time-series 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 'days' parameter has zero schema description coverage, and the description never mentions the time window at all — not the 90-day default, the 7–365 bounds, nor what the window applies to. Only the structured min/max/default let an agent infer intent, so the description fails to compensate for the coverage gap.

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 ('Show how the golfer's swing has changed across sessions') and then enumerates exactly what is returned: Swing Score, skill scores, On target stats, focus scores, and first-vs-latest medians. That enumeration makes it unmistakable versus siblings like recent_sessions or goals.

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?

Gives an explicit use case ('find their weakest skills before practice_plan') that also sequences it against a named sibling, and explicitly routes goal-progress questions to 'goals' instead. Both the when and the alternative are stated, leaving nothing to inference.

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