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

Annotations only cover the safety profile (readOnly/openWorld/destructive), leaving behavioral disclosure to the text, which delivers strongly: GA4's 4-dateRange ceiling with instructions to split calls, the 9-dimension nested-request accounting for filter dimensions, and the specific trap that a bare numericFilter value validates locally but is rejected at request time. These are exactly the runtime constraints an agent cannot get from structured fields.

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 purpose and a concrete example before the constraint list, and nearly every sentence carries actionable content. The numericFilter explanation runs long with a restated GA4 error string, which is slightly redundant but justified by the severity of the pitfall.

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 a 12-parameter read-only report tool with no output schema, the description covers the tricky behavioral edges (date-range limits, dimension accounting, filter value typing) that would otherwise cause failed calls. Return-shape details are unnecessary absent an output schema, and the remaining minor gap is response/pagination shape.

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 only 58%, so the description must compensate, and it does for the complex parameters: it identifies dimensionFilter/metricFilter as GA4 FilterExpression objects, explains dateRanges override startDate/endDate and support multiple ranges, and gives a full worked numericFilter shape. It leaves the simpler fields (limit, keepEmptyRows, property) untouched, but the gap is minor.

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 specific verb and resource ('Run a GA4 report via the Data API') and describes the core shape (dimensions × metrics over a date range) with a concrete example. It does not, however, explicitly differentiate itself from adjacent report siblings like run_realtime_report, run_funnel_report, or run_gaql_report, so an agent must infer the routing.

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?

There is substantial 'how-to-use' guidance (4-dateRange cap, 9-dimension limit, filter pass-through types, pagination via offset), and the worked example implies usage context. But there is no explicit when-to-use vs when-not or any statement naming an alternative report tool, so usage guidance remains implied rather than stated.

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