keywords_bulk_create_preview

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld. The description adds behavioral context not in those annotations: a hard 100-item cap, one bulk request, support for same- or cross-group items, and aggregated receipt output. It does not discuss prerequisites or error handling, but the added batch semantics are meaningful.

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?

A single, front-loaded sentence that captures verb, scope, batching model, and output aggregation with no 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?

For a tool with a required nested items array and an output schema, the description supplies the key missing context – 100-item cap, cross-group capability, preview semantics, and receipt aggregation. It does not explain profile/ad-account prerequisites, but the schema and annotations cover the rest adequately.

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 50%, with useful descriptions on the ambiguous fields (correlationId format, per-item adGroupId override, profile, adAccountId). The description's 'same- or cross-group' hint reinforces the per-item adGroupId override but adds no detail on the items array, bid, status, or matchType beyond the schema. Baseline 3 is appropriate.

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 states a specific verb and resource (preview keyword creates) with clear scope modifiers: up to 100 items, same- or cross-group, one Apple bulk request, aggregated receipt. This implicitly distinguishes it from keyword_create_preview (single) and keywords_bulk_update_preview (update), though it does not name those siblings explicitly.

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?

Usage is implied by 'bulk request' and 'up to 100' – an agent can infer this is for batching many creates rather than repeated single creates. However, there is no explicit when-to-use/when-not-to-use statement or named alternative, so it remains inference rather than guidance.

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