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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description reinforces it with 'Read-only, free.' More usefully, it discloses interpretation behavior the annotations cannot: three-state like_for_like semantics (true/false/null) and the rule that a delta must not be reported as a result when like_for_like is not true. It says nothing about latency, rate limits, or data-volume behavior.

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?

Front-loaded with the operative question, and the like_for_like caveat is placed where it matters. The middle enumeration ('the moves shipped between them, the scans that ran, and the receipts with what was verified live and the clicks each earned') is prose-heavy and could be tightened, but it earns most of its length by describing return contents.

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 returns and does so: start/end visibility, moves, scans, receipts, and the like_for_like flag. For a single-optional-parameter, read-only tool this is close to sufficient; only finer return details (ordering, empty-state behavior) are unstated.

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% and window_days already documents its 7-90 range, default of 14, and clamp-never-reject behavior. The description only alludes to 'a period' without adding format or default detail beyond the schema, so the baseline 3 applies.

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 resource (the growth scoreboard / proof read) and enumerates its scope: AI visibility at the start and end of the window, the moves shipped, the scans that ran, and the receipts with earned clicks. This is distinguishable from adjacent reads like get_visibility or get_outcomes because it is explicitly a period-over-period comparison tool.

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 a strong use condition (reporting whether a change is real, for a period) and an explicit pre-report rule: always read like_for_like first, and never present a delta as a result when like_for_like is not true. It does not, however, name or exclude sibling tools such as get_visibility or get_outcomes, so routing among the several 'get_*' reads is left to inference.

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