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

Annotations cover read-only, idempotent, non-destructive nature. The description adds valuable context beyond that: the data lag (~2-3 days) and the resulting default range, plus the compare-period behavior. It doesn't describe row limit/pagination behavior, but the lag and compare semantics are meaningful additions.

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 compact sentences, front-loaded with what the tool returns, followed by the key default behavior. No filler.

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 flexible 9-parameter analytics tool with no output schema and poor schema coverage, the description covers the metrics and date defaults but omits what the response looks like (rows per dimension combination) and how pagination works. It's adequate but leaves clear gaps given the complexity.

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 11%, so the description needs to compensate but doesn't. It mentions dimensions, filters and compare semantically, but does not explain 'type' (web/image/video/news), startRow/rowLimit pagination, or the filter operators, leaving most of the 9 parameters undocumented by text.

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 ('grouped by dimensions'), the metrics (clicks, impressions, CTR, position) and filter capability. It doesn't explicitly distinguish itself from siblings like gsc_top_queries or gsc_top_pages, but the generic dimensional grouping concept is clear.

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 no guidance on when to use this generic analytics tool versus the many specialized siblings (gsc_top_queries, gsc_device_country_breakdown, etc.). The only usage hint is the default date range and compare flag, not selection criteria.

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