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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the tool is safe. The description adds valuable details about cost tiers, the quote confirmation process for larger sizes, and the fact that repeated known-empty lookups are free, which are not covered by annotations. It also notes country-specific data limitations (ChatGPT vs Google AI Overviews), enhancing transparency.

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 concise but packed with essential information: purpose, cost, confirmation steps, and return details. The key purpose is stated first, followed by cost and confirmation logic, making it easy to scan. No redundant sentences.

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 all necessary operational aspects: cost, confirmation, free repeats, return structure, and country-specific data behavior. With no output schema, it explains what the tool returns (top limit pages and total_count), which is sufficient for an agent to call it correctly.

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 100%, with each parameter well-described. The description adds context on how size affects cost and confirmation, and clarifies limit vs size semantics. It also explains the confirm_quote_id lifecycle, which is critical for correct invocation and not evident from the schema alone.

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 what the tool does: it identifies which of a domain's pages are cited by AI answers, along with mentions, AI search volume, and co-cited domains. It uses specific terms that distinguish it from siblings like ai_sources or ai_overview, and the title reinforces the purpose.

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 provides clear context on when to use this tool (to see AI citations for a domain) and includes cost and confirmation requirements for larger sizes. It doesn't explicitly mention alternatives or when not to use it, but the clarity of purpose and cost details give solid guidance.

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