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

Annotations already establish that this is a read-only, non-destructive, closed-world operation. The description adds useful behavioral context by noting that `roas` includes blended totals and explicitly-unattributed revenue, and it warns the agent to keep attributed and blended figures separate when reporting.

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 compact and front-loads the view distinctions, with each sentence mapping to a specific view. It is efficient, though it starts with view names rather than an explicit overall purpose sentence, which the title supplies instead.

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 read-only, multi-view reporting tool with full schema coverage and annotations, the description is largely complete. Since there is no output schema, the view-by-view explanation of returned metrics is especially valuable; the main gap is the lack of routing guidance against similar sibling analytics tools.

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 `view`, `days`, `since`, `until`, and `provider`, including their view-specific applicability. The description explains what each view returns but does not add syntax, defaults, or other meaning beyond the schema's parameter documentation.

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 enumerates the three view outputs: `roas` for per-campaign spend, attributed users, revenue, CPI, CAC and ROAS; `spend` for raw daily ad-spend rows; and `links` for tracking links. It is specific about the resource being retrieved, though it does not explicitly distinguish this tool from sibling analytics/attribution tools such as `get_attribution_report` or `get_analytics`.

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 view descriptions imply when to choose each view: `roas` for campaign performance metrics, `spend` for raw daily ad-spend rows, and `links` for tracking links. However, it gives no explicit when-not guidance or comparison to sibling tools that also report attribution or analytics data.

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