performance

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavioral context beyond annotations: the test-account failure mode ('test accounts serve no ads and return no metrics') and level-specific metric composition (impression share / budget-vs-rank at campaign, ad strength at ad). No contradiction with 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 states the core purpose and levels, the second adds differentiating metric details, the third states access requirements and the failure mode. The most important scoping information is front-loaded in the first sentence, with no filler or redundancy.

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?

The output schema exists, so return values need no explanation. However, with 9 parameters at 0% schema coverage and closely related siblings (keyword_performance, ad_asset_performance, geo_performance), the description covers access prerequisites and level differences but never addresses how to construct a valid call for the remaining parameters (segment, limit, include_zero_impressions, campaign_id) or how to combine start_date with date_range.

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 0%, so the description carries the burden. It partially compensates by clarifying the 'level' parameter's valid values ('campaign, ad group, or ad level') and the date-range concept, but provides no guidance on limit, segment, customer_id, campaign_id, or include_zero_impressions. For a 9-parameter tool with zero schema descriptions, this is meaningful but incomplete compensation.

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 clear resource ('Performance metrics') and scope ('at campaign, ad group, or ad level over a date range'), implying the retrieve/get verb. The mention of impression share at campaign level and ad strength at ad level provides specificity that helps distinguish it from sibling tools like keyword_performance or ad_asset_performance, though it doesn't name those siblings explicitly.

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 gives concrete when-to-use context: 'Needs Basic access and a live campaign — test accounts serve no ads and return no metrics.' This tells an agent the preconditions for a successful call and a clear failure mode. It doesn't explicitly name alternatives by sibling tool name, but the level scoping implicitly routes keyword/asset/geo level queries elsewhere.

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