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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds operational behavior beyond that: rows past limit are silently dropped, the 200 cap is hard, and a single higher-limit call is preferable to two calls. It does not describe what a row looks like or how detail affects volume beyond the schema's own note.

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?

Three sentences, front-loaded with the verb and scope, then the alternative datasets, then the operational caveat. The dimension enumeration is dense but every item is load-bearing for enum selection; no filler sentences or restated title material.

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?

For an 11-parameter tool with no output schema, the description covers dimension choice, filter composition, time-window defaults, truncation behavior and the special event_properties pairing. The remaining gap is the return shape (value column plus visits/metric columns and how detail changes columns), which the agent must infer.

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 description coverage is 91%, so parameters are already well documented and the baseline is 3. The description adds some mapping value by expanding enum names into human concepts ('sources' = traffic sources or UTM campaigns, 'pages' = all/entry/exit) and by tying event_name to event_properties, but it repeats schema content on filters and limit rather than extending it.

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 ('Ranks one dimension by visits over a window') and then enumerates the concrete dimension families (pages entry/exit, sources, geo, devices, outbound clicks, custom events) so an agent can map intent to a dimension value without trial and error. It is clearly distinct from siblings like get_overview and get_timeseries, which return aggregates over time rather than per-value rankings.

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 concrete routing guidance: use filters to produce segmented breakdowns with a worked example, and switch dimension to crawlers/links/event_properties for the non-visit datasets. It also warns to raise limit instead of double-calling. What it lacks is explicit when-not-to-use guidance naming the sibling tools (e.g. use get_overview for totals or get_timeseries for trends).

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