Cited domains and pages

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

Annotations already cover readOnly/idempotent/non-destructive. The description adds genuinely useful behavior: it is UNFILTERED by ownership, only four AI engines yield citations, and date ranges are bounded by a retention window. It does not describe pagination or result shape beyond the per-source 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-loads the core purpose and the groupBy distinction, then layers scope caveats. The closing 'answers questions like...' sentence is somewhat redundant with the opening but is not wasteful enough to penalize heavily.

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 usefully enumerates returned metrics (citation count, distinct answers, tracked queries, average rank), which an agent needs. Combined with the retention and engine caveats, it is nearly complete for an 8-param read tool, though pagination behavior remains unspecified.

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 only 25% across 8 params, so the description carries a real burden. It explains groupBy and what each source metric means, but groupBy/engines already have schema descriptions, and limit, offset, dateFrom, and dateTo go unexplained in both places. Partial compensation only.

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+resource (cited domains/pages) and distinguishes the two grouping modes (groupBy=domain vs page) in the first clause. It also clarifies the scope as sources of AI answers, setting it apart from sibling tools like get_mention_mix or get_share_of_voice_formula.

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?

Gives clear context: the list is unfiltered by ownership (brand/competitors/third-party), only AI engines produce citations, and dates must fall within retention. However, it names no alternative tool for filtered or non-citation views, so the when-not path is left implicit.

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