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

Goes well beyond the annotations (readOnly/idempotent/closed-world), which already cover the safety profile. It discloses the 366-day ceiling, the auth scope, that nothing is fabricated (not_measured with null rates when nothing is stored), how the rate denominator is defined, that failures/pending/unknown are reported separately, and that it flags truncated/wholeStoredPeriod with unknown coverage for absent weeks.

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-loaded with the core action and scope, and nearly every clause carries operational information (permissions, no-provider-call, not_measured, paging). It is telegraphic and slightly run-on, with a glued token ("at most366inclusive days") and a dense mix of parameter and return-value guidance, but little is genuinely redundant.

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 an 8-parameter tool with a nested dateRange, 0% schema coverage, and no output schema, the description is unusually complete: it names key response fields (truncated, wholeStoredPeriod, nextOffset, not_measured) and the rate denominator. Remaining gaps are the meaning of dateBasis and sourceKind and any explicit return shape for the series rows.

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 0%, so the description has to carry parameter meaning and it only partly does: it clarifies the dateRange's 366-day bound, mentions the optional collectionMode filter, and notes maxMeasurements mirrors the summary tool. It says nothing about dateBasis (observed_at vs created_at), sourceKind, or how limit/offset interact beyond a vague paging hint.

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 and resource ("Read existing tenant-bound evidence") plus the exact shape of the return: a Monday-based UTC weekly time series capped at 366 inclusive days. It also anchors itself to the sibling get_ai_visibility_summary for shared date/maxMeasurements semantics, so an agent can tell it apart from the summary and measurement tools without opening the schema.

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 operating context: this reads already-stored evidence, requires marketing:read, and makes no provider call, which implicitly routes fresh collection to the measurement sibling. It also tells the agent to follow nextOffset for cohorts. It stops short of naming explicit when-not conditions or calling out get_ai_visibility_summary/get_ai_visibility by name as the alternative.

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