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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds real behavioral context beyond them: results are from cached/finalized data ('no refresh, provider call'), coverage is limited to plan-mapped pages, and figures carry no causal-lift interpretation. Only missing piece is pagination/return-shape behavior implied by limit/offset.

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 no filler and the content (what rows, what samples) is front-loaded before the constraints. The telegraphic phrasing ('prior28day', 'Plan-limited mapped pages') costs some readability 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?

With no output schema the description must carry content detail, which it does reasonably well, but for a 7-parameter tool at 29% schema coverage it leaves parameter meaning and tool-selection guidance unaddressed. Adequate for what the data is, thin for how to call it.

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 29% across 7 parameters, so the description must compensate and does not. It mentions dimensions (query/page/country/device) but never ties them to area, direction, days, limit, or offset, leaving enum and paging semantics undocumented 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?

Names the concrete resource: saved finalized query/page/country/device rows plus prior-28-day samples. It doesn't explicitly say 'read' (that lives in the title) and never names a sibling like read_search_rank_history or read_page_insights, but the 'saved, not live provider call' framing separates it from a live-fetch tool.

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?

No when-to-use guidance and no alternative named, despite ~10 read_* siblings that could plausibly be chosen instead (read_page_insights, read_search_rank_history, read_visibility). The 'no refresh, provider call or causal lift claim' line is a constraint statement, not routing guidance.

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