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

Annotations already establish readOnly, non-destructive, closed-world, so the description carries a lower burden. It does add two genuinely non-obvious behaviors: window_days is floored to 1/7/14/28/30/60/90 and time_zone resolves to the workspace zone. Beyond that it says nothing about pagination (cursor/page/page_size), defaults, or how attribution/model changes the result, which for a 29-parameter tool is a real 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?

Two dense sentences with no filler, and the drill-down scope is front-loaded ahead of the caveats. The telegraphic notation ('1/7/14/28/30/60/90', 'spend, ROAS, CPA by model') costs a little readability but is space-efficient.

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?

With 29 parameters, no output schema, and no parameter descriptions, the description should tell the agent what the table returns, how paging works, and what the view/level defaults are. It covers only the date-window quantization and time zone, leaving an agent unable to call this correctly without trial and error.

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 coverage is 0%, so the description must compensate, and it only addresses two of 29 parameters (window_days, time_zone). The hierarchy phrase loosely maps to level values and 'by model' to the model enum, but view, metrics, compare/compare_to, qualities, confidences, parent, order_source, and the paging trio are documented nowhere at all.

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?

States a specific resource (media buying performance table) and the drill-down hierarchy channel→account→campaign→ad set→ad with the metrics it reports (spend, ROAS, CPA by model, compare). An agent can tell what it returns without opening the schema, but the description never distinguishes it from the close sibling ads_breakdowns_get.

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?

No when-to-use, when-not-to-use, or alternative routing is given; ads_breakdowns_get and analytics_query are obvious candidates the description never mentions. The only implied usage is 'drill down and compare', which the agent must infer from the hierarchy notation.

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