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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), yet the description adds substantial semantics an agent cannot get elsewhere: ratios are derived from raw counts, windows ending yesterday exclude today, purchases count as a single action type, and zero-impression rows are dropped. These rules materially affect how results should be interpreted and trusted.

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?

Five tight sentences, each carrying distinct information: scope, metric derivation, window boundaries, counting rule, row filtering, and parameter guidance. Scope is front-loaded and nothing is repeated from the schema or annotations.

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?

For a 7-parameter analytics tool with no output schema, the definition covers level, window, breakdown, and increment semantics plus result-interpretation rules. The only gap is the returned row/column shape, which the agent must infer from the metric list.

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 only 29%, so the description must compensate, and it largely does: it explains the level enum, the since/until format and account-timezone convention, the breakdown dimension options, and time_increment's day-vs-all behavior. It leaves entity_ids and the date_preset values to the schema, which already documents them adequately.

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?

Opens with a specific verb+resource ('Performance for a window') and enumerates the supported levels and breakdowns, so the agent knows exactly what data shape it gets. It does not, however, distinguish itself from the sibling get_performance_report, leaving the agent to guess which read tool to pick.

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 final sentence gives real guidance on parameter selection ('Use since/until ... instead of date_preset'), which is useful. But there is no guidance on when to use this tool versus get_performance_report or get_creative_fatigue, and no stated prerequisites, so tool-selection guidance is only implied.

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