get_campaign_performance

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The verb 'get' implies a read operation, but the description does not explicitly state that it is non-mutating, requires authentication, or has rate limits. It also does not disclose whether results are paginated or if there are any side effects. For a read-only retrieval tool with no annotations, this is a significant gap.

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 concise: a single purpose line followed by a structured Args block. Every sentence earns its place—the purpose line states the outcome and metrics, and the Args block documents each parameter without fluff. It front-loads the core purpose and does not waste words on narratives. This is exemplary structure for a tool description.

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 relative simplicity (three parameters, one required) and the presence of an output schema (which presumably defines the return structure), the description covers the essential invocation details: parameter formats, defaults, and optionality. It does not mention any limitations like account access scope or timezone handling, but these are likely inferable from the context or covered by the output schema. The description is complete enough for an agent to call the tool correctly, though it lacks explicit edge-case warnings that would push it to a 5.

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?

The schema provides only titles and types with no descriptions (schema description coverage is 0%). The description's Args block fully compensates by explaining each parameter: customer_id is a 10-digit Google Ads ID with optional dashes, date_range is a GAQL literal with examples (LAST_30_DAYS, LAST_7_DAYS, THIS_MONTH), and campaign_id is optional and restricts to a single campaign. This adds substantial meaning beyond the schema and clarifies format and optionality.

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 opens with a clear verb and resource: 'Get campaign-level performance metrics' and names the specific metrics (impressions, clicks, cost, conversions). This distinguishes it from siblings like get_ad_group_performance and get_keyword_performance, which target different granularities, and from run_gaql which is a generic query tool. The agent can immediately tell what this tool does.

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 implies usage through its phrasing ('campaign-level') but does not explicitly state when to choose this over alternatives or when not to use it. There is no mention of 'use this for campaign metrics, use get_ad_group_performance for ad group metrics' or any exclusions. The optional campaign_id parameter hints at single-campaign filtering, but no guidance on when that is appropriate. This falls under 'implied usage' without clear direction.

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