Preview up to 100 negative keyword creations in one scope to catch errors before applying them to a campaign or ad group.
Preview up to 100 negative keyword creates in one scope.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | ||
| profile | Yes | local Apple Ads profile name | |
| adGroupId | No | ||
| campaignId | No | ||
| adAccountId | Yes | Apple Ads ad account ID |
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| preview | No | ||
| summary | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is known. The description adds the 100-item cap and reinforces the preview-only nature, but says nothing about what the preview returns or how to commit the change, so it contributes only modestly.
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?
One front-loaded sentence with no filler. It is appropriately short, though the brevity borders on under-specification given the tool's complexity.
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 output schema covers return values, and annotations cover safety, so the description doesn't need those. But for a scoped bulk-preview tool it should clarify the campaign-vs-adGroup scope choice and the items structure; those gaps prevent it from being complete.
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 only 40%, and the description compensates minimally: it implies the items array and a single scope selector but never explains matchType, status, or the fact that campaignId and adGroupId are the mutually-exclusive scope parameters. The critical 'one scope' ambiguity between campaign vs ad group is left for the agent to infer.
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?
Specific verb (preview creates) plus resource (negative keywords), with a bulk cap of 100 that distinguishes it from the single-item negative_keyword_create_preview. However 'in one scope' is vague — it doesn't clarify whether scope means campaign-level or ad-group-level, and it doesn't name the sibling it replaces.
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?
No explicit guidance on when to use this instead of negative_keyword_create_preview or negative_keywords_bulk_update_preview, and no statement of what to do after previewing (e.g. apply via operations_apply). The 'preview' wording implies non-mutating intent but no alternative routing is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.