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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds non-obvious behavior: a hard top-20 cap, cost-based ranking, the yesterday cutoff, and the silent exclusion of zero-cost ads — all things an agent would otherwise get wrong.

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?

Front-loaded with the core statement, then caveats, then the parameter note — a sensible order. The field enumeration is somewhat long and partly duplicates the output schema, but it stays readable and earns most of its space.

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 two-parameter read-only report with an output schema, the description covers scope, ranking, time window, exclusions, and the alternative tool. The only gap is the undocumented 'days' parameter default/limits.

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 explains workspace well (slug, optional when only one workspace), but only alludes to the days parameter ('letzten N Tage') without naming it, stating its default, or clarifying valid ranges.

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 precisely what the tool returns: the top 20 ads ranked by cost over the last N days up to yesterday, with an explicit field list. It also distinguishes itself from ads_list_ads (full list) and implicitly from ads_campaign_performance / ads_keyword_performance by scoping to ad level.

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?

Gives clear usage boundaries: today is excluded, ads without cost are omitted, and ads_list_ads is named as the route for a complete list. It does not compare against sibling performance tools (campaign/keyword), but the when-to-use context is otherwise explicit.

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