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

Beyond the annotations (readOnlyHint=true, destrctiveHint=false), the description discloses behavior annotations can't express: results are sorted by spend, the returned metric set, and critically the pagination contract (truncated=true, offset=next_offset, never treat one page as complete). This directly prevents a common integration failure — stopping at page one — and is exactly the kind of beyond-the-annotation trait a query tool should reveal.

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?

Three sentences, no filler: the first states purpose and output shape, the second enumerates filter dimensions, and the third carries the high-stakes pagination warning with emphasis ('never treat one page as complete'). Every sentence earns its place and the most operationally important guidance is front-loaded last for vividness without bloating the entry.

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?

Given the complexity (20 parameters, no output schema), the description covers the essential invocation contract: return metrics, sort order, filter capabilities, and the pagination loop required to reach the FULL dataset. The residual gap is that the date-scoping parameters (start_date, end_date, period_days) have empty schema descriptions and are not addressed in the description, which is a minor but real hole for a time-series ad metrics tool.

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 85%, so the baseline of 3 applies and the schema already documents most parameters well (e.g., parent_asin, min_clicks, offset all carry rich descriptions). The description adds modest semantic framing by mapping its stated filters ('search term text, campaign name, metric thresholds') to parameter groups, plus reinforcing the offset/next_offset contract, but it does not compensate for the few undocumented date parameters (start_date, end_date, period_days) that fall in the remaining 15%.

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?

The description opens with a specific verb and resource ('Query search term performance data') and details the exact return shape: terms sorted by spend with the metric list (cost, sales, ACos, clics, impressions, purchases, CVR). This is concrete enough to distinguish it from siblings like ppc_keywords (keywords, not search terms), ppc_campaigns, and brrand_top_search_terms — the metric list and spend-sort order make the resource unambiguous.

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?

The description implies usage context by naming the tool's resource (search-term performance, with metric thresholds and text/campaign filtering) but never states when to pick this over alternatives such as ppc_keywords, ppc_product_report, or pp_cquery. There are no exclusions or explicit alternative routing; the invocation guidance that exists is about paging within this tool ('never treat one page as complete'), which is valuable but is not when-vs-alternative guidance.

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