get_ads_keywords

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description layers on real behavioral context: the 28-day window, spend-based ordering, the exact metric columns, the tracked:false sentinel for organic rank, and connected=false indicating Apple Ads is not linked. Pagination or result limits are not mentioned, keeping it short of a 5.

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 paragraph that leads with what the tool returns and what the rows are sorted by, then handles the parameters and the disconnected-state edge case. It is dense and slightly run-on with the long metric list, but nearly every clause carries information.

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 burden of describing the return shape and does so thoroughly (columns, ordering, tracking flag, connection flag), and annotations cover safety. It stops short of stating row limits or pagination behavior for what can be a large per-app keyword set.

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%, so the schema already documents appId, country, and campaign. The description reinforces the campaign narrowing and country/organic-rank relationship but adds little syntax or format detail beyond the schema, matching the baseline 3.

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?

States a specific verb and resource ('Every Apple Ads keyword bought for one app across its campaigns') plus scope (last 28 days) and even the returned columns, which separates it from organic keyword tools like get_keywords and from ad query tools like get_ads_search_terms. It does not name a sibling alternative explicitly, so it is clear but not fully self-differentiating.

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 the scope and by 'Pass campaign to narrow to one campaign', which tells the agent how to constrain results but not when to reach for this tool over get_ads_campaigns, get_ads_search_terms, or get_keywords. No when-not guidance is given.

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