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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description goes beyond them with the top-50-by-cost cap, the exclusion of today from the window, the quality_score 1-10/'N/A' semantics, and the definition of conversions as primary/bid-relevant. These are exactly the behavioral facts an agent needs. It stops short of describing pagination or ordering ties.

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 leads with what the tool returns and the time window, then adds caveats, alternatives, and parameter notes. It is dense but every sentence carries information. Some subject changes (QS scale, conversions definition, workspace) make it a bit choppy and it mixes German and English.

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 an output schema present, the description need not enumerate return fields, and it still covers the key semantics (top-50 ranking by cost, QS range, conversions meaning). Combined with the annotations and sibling routing, an agent has enough to call it correctly, though the default day count is missing.

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%, but the description compensates: 'days' is explained as the last N days through yesterday (today excluded) and 'workspace' as the customer workspace slug that is optional when only one workspace exists. Neither parameter has a schema description, so this added meaning is valuable. A 5 is held back only because the default (14) is not acknowledged.

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 verb+resource with scope: 'Top 50 Keywords nach Kosten der letzten N Tage bis gestern', listing what is included (Quality Score, CPC, Conversions). It distinguishes itself from ads_list_keywords by explicitly saying it is not a complete dump. An agent can tell exactly what this returns.

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?

Explicitly names the alternative for full coverage ('für alle Keywords ads_list_keywords') and routes QS component questions to ads_keyword_quality. The 'bis gestern (heute nicht enthalten)' boundary clarifies when the window applies.

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