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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable coverage context — SB/SD scope, no AMC dependency, and SP exclusion — beyond the annotations. It does not disclose the output structure, row granularity beyond 'per campaign,' or how the days parameter shapes results, so transparency is partial but acceptable for a read-only report.

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?

Two concise sentences with zero filler. The core metric and aggregation level are front-loaded, and each sentence earns its place: one defines what the tool returns and its data source, the other sets an expectation about SP exclusion.

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, two-parameter report whose safety profile is covered by annotations, the description is adequate but has clear gaps: the meaning of 'days' is unexplained, no output schema exists so return structure is undescribed, and there is no explicit routing guidance versus sibling ppc_* tools. The metric definition, ad-type scope, and data-source note cover the essentials.

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 50%: only profile_id has a description. The tool description mentions neither parameter, leaving 'days' entirely undocumented — no default, range, or lookback-window semantics. Since coverage is not high (>80%), the description should compensate for the undocumented parameter but does not.

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 names a specific verb and resource: it reports 'New-to-brand purchases/sales and NTB% per campaign,' expanded from the cryptic NTB abbreviation in the title. It also scopes coverage to SB + SD and explicitly excludes SP, which helps distinguish it from the many sibling ppc_* report tools. It stops short of naming a specific alternative tool, but the purpose itself is unambiguous.

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?

There is useful usage context: the data comes 'from standard report columns — no AMC needed,' and 'SP has no NTB data' is a partial exclusion informing the agent which ad types not to expect. However, it never states when to prefer this tool over siblings such as ppc_campaigns, ppc_campaign_details, or ppc_conversion_funnel, nor does it name alternatives. The intended usage must be inferred from the NTB focus.

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