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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, covering the safety profile. The description adds genuinely non-obvious behavior beyond annotations: the tiered credit cost (6/12/22), the free-on-known-empty-repeat caching, and the two-phase quote-then-confirm flow for sizes 200/500 (confirm_quote_id). This aligns with idempotentHint=false and adds real operational context.

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?

Roughly five purposeful sentences with the core purpose front-loaded before cost and return details. Every sentence earns its place, though the credit/quote information is dense and slightly packed together. Still, there is no filler or redundancy.

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 5-parameter tool with an enum, a cost model, a two-phase quote confirmation flow, and no output schema, the description covers the essentials: purpose, credit costs, the mention-data country limitation, the confirm flow, and the return shape (top limit domains, total_count, total answers). The trickiest operational aspect, the quote-first call for 200/500, is explicitly explained, so an agent can invoke 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%, so the baseline is 3. The description adds cross-parameter value beyond the schema: it maps size to cost and clarifies that sizes 200/500 require the confirm_quote_id round-trip, and it surfaces the country nuance (ChatGPT mention data exists for 'us' only; other countries are Google AI Overviews only) — a detail the schema's country description omits.

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 opens with a specific verb-resource-scope statement: 'Which domains AI answers cite most for prompts containing a topic, with mentions, share and AI search volume.' This clearly differentiates ai_sources from its AI-family siblings (ai_check, ai_overview, ai_prompts, ai_trend) by focusing on cited/owned domains. The phrase 'see who "owns" a topic in AI search' adds a sharp, memorable 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 gives a clear use context ('Useful to see who owns a topic in AI search') and explains operational behavior (cost, quote flow), but it never names an alternative tool or states when NOT to use it. Unlike a high-scoring definition that explicitly routes to a sibling, this one leaves tool-selection among the six AI siblings to inference.

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