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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so safety is covered. The description adds a genuinely useful constraint not in the annotations or schema: a maximum 31-day window, which directly bounds how the date parameters may be used. It also explains the baseline used for click intensity ('vs the expected uniform share'), which is real behavioral context.

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, no filler, and the core action plus its constraint (one page, max 31 days) is front-loaded before the return-value detail. Parenthetical lists are dense but each element carries information an agent needs.

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 should explain what comes back, and it does: scroll-depth percentile thresholds and graded click intensity with shares. Only minor gaps remain, such as behavior on pages with too little traffic or whether results are device-segmented by default beyond the schema's default value.

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%, so the baseline is 3; the description earns a bump because the 31-day maximum window materially constrains start_date/end_date, a limit that appears nowhere in the schema. It also clarifies that results are scoped to a single page pathname, reinforcing the required-parameter intent.

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?

Names a specific verb and resource ('How visitors actually interact with one page') and immediately enumerates what comes back: scroll depth at 75/50/25 percent session thresholds plus per-element click intensity and click shares. This clearly separates it from aggregate siblings like get_top_pages or session-level tools like get_session_replay.

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: 'Use to understand attention and dead zones on a page before proposing UI changes.' That is clear context for when to reach for it, but it names no alternatives or exclusions (e.g., when to prefer get_top_pages or session replay instead).

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