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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context beyond those annotations: it returns raw daily rows, uses inclusive YYYY-MM-DD dates, and operates at exactly one aggregation level per call. This helps set expectations without contradicting the annotations.

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?

Three sentences, each earning its place: the first defines the resource and metrics, the second specifies date format, and the third routes to the alternative tool. The most important scoping detail ('raw daily' and 'one aggregation level') is front-loaded. No filler or redundant restatement of the schema.

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?

Given the tool's moderate complexity, full schema coverage, and safe annotations, the description covers the essential decision points: what is returned, at what granularity, over what date range, and which sibling to choose for a different need. The absence of an output schema is partially compensated by explicitly listing the returned metric fields. No critical information 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 description coverage is 100%, so the schema already documents every parameter, including the date format, entityType enum, platform default, and workspaceId fallback. The description adds little parameter-level meaning beyond what the schema provides; it only reinforces 'aggregation level' and the inclusive date format. 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 uses a specific verb ('Get') and resource ('raw daily ad metric rows'), enumerates the exact metrics returned, and lists all four aggregation levels. It also explicitly contrasts itself with campaignstack_get_ad_dashboard ('summarized view'), making its purpose unmistakable.

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 description clearly states when to use this tool: when raw daily metric rows are needed. It names the alternative tool (campaignstack_get_ad_dashboard) and the condition ('summarized view') that should select that sibling instead. This gives an agent actionable routing guidance.

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