ad_performance

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

Annotations already indicate readOnlyHint=true. The description adds significant behavioral details: returns specific metrics, derived values (CTR, CPC, CPM), joined conversions, cost-per-conversion, flag logic with thresholds (dead/underperforming/ok), worst-first sorting, and data freshness caveat (partial same-day data). This fully discloses the tool's behavior beyond the annotation.

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 extremely concise with no wasted words. Two dense sentences and a brief list of returned fields. Key points are front-loaded: purpose, date range, flagging. Every sentence adds value without 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?

Given the tool has 6 parameters (2 required), an output schema (so return values are covered), and readOnlyHint annotation, the description covers all behavioral aspects: input (date range), processing (thresholds for flags), output (metrics and flags), and edge cases (partial same-day data). No additional information is needed for an agent to select and use this tool correctly.

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 must compensate. It only indirectly explains the flag thresholds through the flag definitions (dead: enough impressions, ~no clicks; underperforming: very low CTR) which relate to parameters min_impressions, dead_max_clicks, underperf_max_ctr. However, the description does not explain each parameter individually, such as since/until format (though it mentions inclusive date window) or the exact meaning of default values. An agent would have to infer parameter roles from flag logic.

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 clearly states the tool returns per-ad performance over a date window with derived metrics and flags (dead, underperforming, ok). It uses specific verbs and resources (returns impressions/clicks/spend with derived CTR/CPC/CPM and flagging). It distinguishes from sibling tools like get_insights or account_overview by focusing on ad-level performance with weak ad detection.

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 mentions inclusive date window and partial same-day data, providing context on when to use (e.g., not for real-time accurate data). However, it does not explicitly state when to use this tool versus alternatives like get_insights, which might also return ad performance data. No exclusion or alternative recommendations are given.

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