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

The description goes far beyond the annotations by disclosing that duplicate keywords are skipped, clustering and intent classification run asynchronously, and the credit is charged even if all keywords were already tracked. It also states the rate limit, credit cost, non-refundability, and subscription requirement. This gives the agent a strong understanding of real-world behavior and side effects.

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 is dense but every sentence provides necessary operational detail: what the tool does, what it skips, background processing, rate limits, credit costs, auth requirements, and alternative routing. Despite its length, it is well-organized and front-loads the core behavior before secondary caveats.

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?

The description covers prerequisites, quota limits, cost implications, failure behavior, asynchronous effects, parameter requirements, and sibling tool differentiation. Together with the output schema, an agent has everything needed to invoke the tool correctly and anticipate outcomes.

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?

While the schema already documents all parameters, the description adds critical semantics: confirm=true acknowledges the credit charge, omitting it returns only the cost and balance, and website_id is needed only for multi-website accounts. The exact keyword count range and the 'exactly as written' behavior add meaning beyond the schema's field names and types.

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?

The description clearly states the tool adds given keywords to the keyword plan exactly as written, with volume, difficulty, and CPC from the provider. It differentiates itself from research_keywords by explicitly noting that nothing is expanded or invented and that research_keywords is for discovering related ideas. This makes the tool's purpose unambiguous.

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 description gives explicit when-to-use guidance, including the alternative research_keywords for discovery use cases. It also details limits shared with research_keywords, the confirm=true requirement, and the website_id field conditions. The agent knows exactly when to call this tool versus others.

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