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

Annotations already declare readOnlyHint, destructiveHint=false and closed-world, so the bar is lower, yet the description still adds real substance: no cost, the three-state like_for_like semantics including the null case, and the warning that a non-true value means a new baseline rather than a rise or fall. It also discloses the trailing-28-day nature of traffic totals and the one-week-minimum comparison gap, which no annotation conveys.

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 purpose hook is front-loaded and nothing is filler, but the body is one dense run-on block mixing return contents, like_for_like semantics, and traffic caveats without separation. A reader has to parse 28-day-window and comparison rules out of a single long sentence.

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, so the description carries the full return-value burden, and it does: visibility start/end, moves, scans, verified receipts, clicks, and the traffic breakdown. Combined with the like_for_like contract and the single well-documented parameter, an agent has enough to call it and interpret the result correctly.

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% for the single window_days parameter, so the baseline is 3. The description adds beyond the schema by explaining what the window governs for traffic — trailing totals over window_days versus a previous reading gap_days older — which clarifies downstream meaning rather than restating the range or clamping rule.

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 names a concrete composite artifact: AI visibility at the start and end of a window, moves shipped, scans run, and receipts with verified live results and clicks. That is a specific verb+resource, distinguishing it from a single-metric sibling like get_visibility. It never names an alternative sibling, so an agent must infer the boundary from content alone.

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?

It gives a strong interpretive precondition: always read like_for_like before reporting a change, and never present a delta when like_for_like is not true. It also states the comparison rule for traffic (only against a reading on the same property at least a week older). It stops short of saying when to reach for this tool instead of get_visibility, get_seo, or get_activity.

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