get_insights

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

Annotations already declare readOnlyHint=true, and the description adds behavioral details beyond that: handling of the 'until == today' quirk, and requirement that fields match the aggregation level. This adds context without contradicting annotations.

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 concise with no wasted sentences. It front-loads the purpose and then adds parameter details, a behavioral note, and a sibling recommendation, all in few sentences.

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 presence of an output schema, readOnlyHint annotation, and sibling tools, the description provides sufficient context: purpose, key parameter semantics, a behavioral quirk, and guidance when to use an alternative. It covers all essential aspects for an agent to select and invoke the 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?

With 0% schema description coverage, the description compensates by explaining aggregation_level (enum options), fields (default and level matching), and mentions the until quirk. However, it does not describe the 'since' and 'limit' parameters, so it is not fully comprehensive.

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 states 'Escape hatch for raw insight rows at a given aggregation level,' which is a specific verb and resource. It distinguishes from sibling tool 'ad_performance' by directing to it for a common task, thus providing differentiation.

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 explicitly tells when to use this tool ('escape hatch' for raw insights) and when not to ('Prefer ad_performance for the common find weak ads task'). It also explains the aggregation_level options and default behavior for fields.

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