google_ads_ad_performance_compare

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

No annotations are provided, so the description carries full burden. It discloses the read-only nature ('does not pause or rotate ads'), the scoring formula (ctr*cvr, or ctr if conversions=0), the threshold for insufficient data, and the return structure. It does not cover rate limits or auth, but for a read-only analysis tool this is acceptable.

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 dense but efficient. It front-loads the main purpose and return structure. While slightly long, every sentence adds value—no filler. The structured representation of the return object in curly braces is concise and informative.

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 complexity (ranking, multiple metrics, verdict logic, thresholds) and the absence of an output schema, the description covers all critical aspects: scoring rule, threshold, verdict assignment, read-only nature, and sibling differentiation. It is complete for an agent to correctly invoke the tool.

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%, and the description adds substantial context beyond the schema: for customer_id it explains fallback to configured credentials; for period it gives usage recommendations; for ad_group_id it explains why it's required (scope to one ad group for shared targeting) and how to obtain it via a sibling tool.

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 starts with a clear verb+resource: 'Rank ENABLED ads within a single Google Ads ad group and assign WINNER / LOSER / INSUFFICIENT_DATA verdicts.' It immediately distinguishes the scope (single ad group) and outcome. It also explicitly names sibling tools for cross-ad-group or RSA analysis, eliminating ambiguity.

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 provides explicit when-to-use guidance: it explains the threshold for INSUFFICIENT_DATA (impressions < 100), the verdict logic (ties get WINNER, rest LOSER), and states it is read-only. Parameter descriptions further guide period selection ('shorter window for recent changes, LAST_90_DAYS for trend baseline'). Sibling tool references give clear alternatives.

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