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

Annotations already cover the safety profile (readOnly, idempotent, openWorld=false), and the description adds real behavioral context beyond them: sorted by cost descending, cursor pagination, data-completeness caveats on recent days, and the bid-adjustment override rules (ad group overrides campaign except campaign -100%).

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?

Front-loads the core purpose, then progressively adds metrics, scope, level semantics, and bid-adjustment rules. It is dense and runs long, but nearly every clause carries information an agent would otherwise have to guess; the metrics enumeration is the only borderline section.

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 return-value burden and does so: it lists the metrics, explains bid_adjustment_percent/source semantics, states sort order and pagination. Nothing an agent needs to call or interpret this tool is missing.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema — what level actually changes at row granularity and what bid_adjustment_percent / bid_adjustment_source values mean. It also clarifies that level is a plain string rather than encoding an enum.

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 — device-split performance for the last N complete days — and enumerates the metrics returned. It is clearly distinguishable from sibling performance tools such as get_location_performance and get_search_terms by naming the device dimension and the campaign-only scope.

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?

Gives clear context: 'Search campaigns only', the level=campaign default vs level=ad_group row semantics, and routes mutation to set_device_bid_adjustments. It does not explicitly contrast against sibling read tools (e.g. get_campaigns) for the same data, but the when-to-use picture is solid.

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