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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; the description adds useful behavioral facts beyond them — results are exact (not sampled), computed server-side, and capped at 20 metrics. However it does not explain the required expectedRevision parameter's conflict/staleness behavior, which is the one genuinely non-obvious behavioral trait an agent needs.

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?

Two dense sentences with the aggregation capability front-loaded and no filler. The closing clause about snapshotRevision is terse enough to be slightly cryptic and would read better explicitly tied to expectedRevision, but nothing is wasted.

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?

An output schema exists, so return-shape explanation is not required, and the description covers the operation set, the metric cap, and the exactness guarantee. The main missing piece, expectedRevision semantics, is real but is the only substantive gap for a read-only idempotent tool.

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 0% schema description coverage the description must compensate, and it partially does: it maps 'metrics' to the operation families and states the 20-metric cap, and 'filters or search' alludes to the query object's q field. It says nothing about expectedRevision (required, nullable, revision-matching semantics), alias uniqueness, or the 10-filter bound, leaving key parameters unexplained in both places.

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 (compute) and resource (exact server-side metrics) and enumerates the supported operations: row count, non-empty count, distinct count, and numeric sum/average/minimum/maximum. It clearly distinguishes the tool as an aggregation operation rather than a row-returning one, but never names a sibling such as sheets_query or sheets_search_rows to make the boundary explicit.

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?

The phrase 'over all rows matching bounded filters or search' implies the tool is for filtered aggregation, and 'Pin repeated analysis with returned snapshotRevision' hints at a repeated-analysis use case, but there is no explicit when-to-use versus sheets_query/sheets_search_rows split and no statement of exclusions or prerequisites.

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