ads_campaign_performance

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

With no annotations provided, the description carries the full behavioral disclosure burden, but it only says 'Gets... metrics for a date range.' Read-only intent is implied by the word 'Gets,' but nothing is disclosed about aggregation level, which metrics are included, date-range limits, timezone handling, or the shape of the response.

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?

A single front-loaded sentence with zero wasted words: verb, object, and scope in that order. The brevity is clean and readable. The thinness of content is a completeness problem, not a structure problem, so it isn't double-penalized here.

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 metrics tool with 3 parameters, a nested dateRange object, and no output schema, a one-sentence description is insufficient. An agent needs to know what metrics are returned (impressions, clicks, conversions, cost), what the optional campaignId does, and which of the many performance-report siblings this replaces. The contract of the tool remains underspecified.

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 only 33% (customerId is the only described parameter; campaignId has no description and dateRange sub-fields only carry format strings). The description mentions 'date range' and 'campaign,' loosely mapping to two parameters, but it adds no semantics for the optional campaignId filter or what happens when it's omitted. Low schema coverage requires more compensation than this.

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 states a specific verb+resource: 'Gets campaign performance metrics for a date range.' The 'performance metrics' phrasing clearly signals aggregated metrics data rather than campaign administration. However, it doesn't explicitly differentiate from near-siblings like ads_get_campaign, ads_list_campaigns, or ads_account_summary, so the agent must infer the distinction.

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 no when-to-use guidance at all. The description never explains when to choose this over ads_search_term_report, ads_account_summary, gsc_query_performance, or gbp_performance_report, nor does it note that campaignId is an optional filter. The only hint is the 'date range' scope, which is implicit context rather than guidance.

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