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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds useful context about aggregation being done server-side in a single call and that dates get min/max rather than sums, but says nothing about result size, limits, or how non-numeric columns are handled.

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?

Everything is packed into one front-loaded sentence that begins with what is computed, then scope, then grouping. The trailing "Free." is terse but adds cost information; the comma-heavy list of aggregates is dense but still parseable.

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 must convey what comes back, and it only implies the shape (an overall summary plus per-group summaries) without describing the result fields or handling of empty column selection. It also omits the column/filter count caps enforced by the schema, leaving the agent to infer limits.

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?

With only 60% schema description coverage, the description compensates well: it explains that filters restrict the summarized row set (and points to rows_query for filter semantics), that group_by produces per-value breakdowns, and that columns are number/date measures. The `match` parameter (all/any) remains unexplained in both schema and description.

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 specific verbs and resources: counts rows and computes sum/average/min/max over number columns (and min/max for dates), overall and per group_by value. It also explicitly contrasts itself with the row-paging alternative, so an agent can distinguish it from rows_query immediately.

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?

"One call instead of paging through every row" clearly signals when this tool is preferable to listing rows, and "Filters work as in rows_query" tells the caller they can reuse filter semantics. It stops short of stating an explicit exclusion (e.g. when to use rows_query instead for row-level data).

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