Insights search terms

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

The annotations already establish that this is a read-only, idempotent, non-destructive operation. The description adds useful behavioral context by explaining that outputs include negative keyword and new keyword recommendations, each with a ready ads.mutate operation. It could be clearer that the tool does not apply those mutations itself, but 'ready' implies a proposed operation rather than execution.

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?

The description is a single compact sentence with no wasted wording. It front-loads the core concept, 'Search-term mining,' and uses clear mapping from term type to recommended action.

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?

The tool is moderately complex with one required parameter and three optional tuning parameters, but the description gives no parameter guidance despite 0% schema description coverage. It benefits from rich annotations and an output schema, but an agent still lacks information about how to set the time window and conversion/waste thresholds.

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?

The input schema has four parameters and zero schema description coverage, so the description should compensate by explaining days, min_conversions, min_waste_cost_micros, and customer_id. It does not mention any parameter names, thresholds, units, or defaults, though the waste/conversion concepts loosely relate to two of the parameters.

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 clearly frames the tool as search-term mining that turns wasted terms into negative keyword suggestions and untargeted converting terms into new keyword suggestions. It is specific about outputs and implied recommendations, though it does not explicitly name sibling tools such as ads.report.search_terms or insights.apply_negatives.

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 intended use is implied by 'Search-term mining' and the mapping to negative and new keywords. However, there is no explicit when-to-use guidance, no exclusions, and no mention of alternatives like ads.report.search_terms for raw reporting or insights.apply_negatives for applying changes.

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