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

Goes well beyond readOnlyHint/openWorldHint by disclosing the critical caveat that rows are capped at 100 terms by impressions and are never complete (limit, min_impressions, terms hidden by Google), so row sums are not totals and coverage must be consulted. It also states the date boundary (complete days up to yesterday, today excluded) and that conversions means primary conversions — exactly the kind of context annotations cannot carry.

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?

Content is front-loaded with the report definition before the per-parameter notes, and essentially every line carries usable information. It is a dense block without explicit list formatting, and the German text sits under an English tool name/title, which adds minor friction for non-German agents.

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 five-parameter analytics tool with an output schema, this covers everything needed: purpose, filters, defaults, the return shape sketch, the incompleteness/coverage caveat, and routing to three alternatives. No gap remains that would cause a mis-call.

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 (and does) document all five parameters: days including its semantics and default, min_impressions with default and a tuning recommendation, campaign_id/ad_group_id as optional filters, and workspace as optional for single-workspace accounts. This fully compensates for the empty schema descriptions.

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 statement ("Search Terms Report — was User wirklich gesucht haben") and immediately scopes it to search campaigns only. It also names the sibling tools for adjacent use cases (ads_pmax_search_insights, ads_ai_max_search_terms, ads_campaign_performance), so the agent can distinguish it from the other search/performance tools without opening a schema.

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 explicit when-to-use conditions and exclusions: set min_impressions to 1 for expensive low-volume spread, use ads_campaign_performance for all-campaign totals, ads_pmax_search_insights for PMax, ads_ai_max_search_terms for the AI-Max source split. Workspace optionality is also stated. Nothing is left to inference.

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