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

Despite annotations already declaring readOnly and non-destructive, the description adds substantial behavior an agent could not infer: UTC day boundaries, the windowing rule that last_N_days ends yesterday while today/this_month/year_to_date include the partial current day and compare against the same elapsed span, and that retention, revenue, and session cards only count finished days. It also documents value conventions (percentages as fractions 0-1, changes as fractional differences), which directly affects result interpretation.

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?

Purpose is front-loaded in the first sentence and every following sentence carries load-bearing information about ranges, comparison spans, or value units. It is a dense single block with no visual structure, which slightly hurts scannability for a description of this length.

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 compensates by describing the return shape (card_data per metric with value, prior value, and delta) and the unit conventions for those values. Combined with the range-resolution rules and default behavior, an agent has everything needed to call this tool correctly and interpret results.

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, but the description adds real semantic depth beyond the schema: it explains what each named range actually covers, how comparison periods are computed for each range type, and that omitting parameters falls back to the dashboard's default range. It does not separately narrate start/end, which the schema already covers for the custom range.

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 gives a specific verb and resource ("Return the account's dashboard KPIs for a date range") and enumerates what a result contains (card_data per metric with current value, prior-period value, and change), naming example metrics such as matches played, unique players, and custom event/report metrics. That is clear enough to distinguish it from the many narrow siblings like get_retention_report or get_event_report, though it never explicitly states the split (dashboard rollup vs. single-domain report).

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?

"Use this for 'how is the game doing' or trend questions" gives a clear positive selection criterion, and the range semantics (last_N_days vs. today/this_month/year_to_date, default range) guide correct invocation. It stops short of explicit exclusions or naming alternative sibling tools for deeper drill-down, so it is a strong 4 rather than a 5.

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