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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so safety is covered. The description adds real behavioral value beyond that: it reports per-row negation state and warns against misreading zero orders on single-digit clicks as poor performance, which shapes how the agent interprets results.

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 sentences front-load the return shape and the usage trigger, with no wasted framing. The closing statistical caution is slightly tangential to describing the tool but earns its place by preventing a common misinterpretation.

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 carries the return-value burden and does so by listing the metric and attribution fields. Parameters are covered by a rich schema, and annotations cover the safety profile, so nothing an agent needs to invoke this correctly is missing.

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 100%, with days, limit, and marketplace_id all fully documented in the schema itself (including the currency-mixing warning and the list_my_marketplaces pointer). The description adds no parameter-level detail, so the baseline 3 applies.

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 names a specific resource (customer search terms that triggered ads) and enumerates the exact payload: clicks, orders, spend, campaign/ad-group attribution, and negation status. The 'ALREADY negated' clause implicitly distinguishes it from get_ads_negatives and get_brand_search_terms without the agent needing to open a 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?

It gives an explicit triggering condition: 'Call this before proposing a negative keyword,' which tells the agent exactly when this tool belongs in a workflow. It stops short of naming when-not-to-use or an alternative sibling to reach for instead, so it is clear context rather than full routing guidance.

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