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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is met without the description. On top of that the description adds real behavioral context: the window is rolling and anchored to `to`, the heatmap is bounded to 6:00–23:00 Mon–Sun, and comebacks use a 90-day lookback and wall-clock minutes of finished sessions as displayed in the app — non-obvious computation details absent from annotations. It stops short of stating timezone handling or response shape, so not a 5.

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?

It is front-loaded with the window definition and contains no filler, but the second half is one long comma-spliced run-on listing five distinct metrics, which makes it hard to scan. A short bulleted metric list would communicate the same content with less parsing cost.

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 return-value burden and does so by enumerating every metric included in the report, which is strong. It leaves out units/timing edge cases (e.g., timezone used to compute daily boundaries, what an empty range returns), which matters for a time-bucketed analytics 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?

Schema coverage is 100%, establishing a baseline of 3. The description still earns credit by adding semantics the schema lacks: it defines week as the last 7 days and month as the last 30 days ending on `to`, clarifying that these are rolling windows rather than calendar periods.

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 establishes that this is a period-reporting tool and enumerates the exact metrics returned (minutes per day, hard/comfortable share, heatmap, main-step days, comebacks), so an agent knows what it gets. It never contrasts itself with the obvious siblings summarize_day and summarize_week, even though the outputs overlap heavily, leaving the agent to guess which reporting tool to pick.

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 only implied via the range/defaults semantics ('default today', 'default week'); there is no explicit statement of when to call this instead of summarize_week, summarize_day, or get_capacity. The comebacks lookback ('over 90 days') is the only scoping hint, and it is presented as a metric description rather than routing guidance.

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