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

No annotations exist, so the description carries the full behavioral burden and does so richly: it discloses that every call hits Google (cost/latency), that average position is impression-weighted across queries/devices/countries rather than a rank-tracker rank, that deep positions are sparse, and that absolute positions are directional only. The paging/truncation disclosure is exactly the kind of caveat 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?

Front-loads the purpose before the POSITION and PAGING caveats, and the labeled sections make it scannable. It is dense, but each clause (impression-weighting, sparse deep positions, truncated flag) carries operational value rather than 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?

With no output schema and no annotations, the description still covers live-computation behavior, data-quality caveats, alternatives, and pagination mechanics including the truncated/next_offset contract. The only gap is that it doesn't enumerate the actual row fields returned, though it fully explains the pagination wrapper.

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 80%, so the baseline is 3. The description adds meaning beyond the schema by tying min_impressions to 'your own impression threshold' and by explaining the offset/limit relationship to the pagination block (next_offset, raise limit), which the schema alone does not contextualize.

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 and scope: it surfaces pages whose CTR is below half the depth-expected benchmark, computed live under the caller's own impression threshold. It distinguishes itself from the sibling Keyword_Rankings explicitly, so an agent can tell them apart without opening either 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 a clear routing rule: prefer Keyword_Rankings for a quick check on a preset window, implying this tool is for the live, threshold-tuned case. It also frames position deltas between periods as the preferred usage. Lacks an explicit 'when not to use' beyond that single alternative.

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