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

The tool has annotations readOnlyHint=true and destructiveHint=false, so the description doesn't need to repeat the obvious read-only/no-destruction behavior. It does add meaningful behavior beyond annotations: 'Cost: 4 credits. Free when the domain has no AI mentions in that country (repeats of a known-empty lookup are free)', and the geographic scope (plus ChatGPT for the US). This is valuable operational context the annotations cannot provide.

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 a few tightly-written sentences with no filler: it starts with the key purpose, adds cost and the free-condition nuance, then says what is returned, and finishes with a helpful sibling pointer. The only slightly redundant part is 'Returns: the summary' after the opening sentence already lists the metrics; still, it's almost entirely useful and front-loaded.

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 no output schema, the description reasonably transmits the key return value: it lists total mentions, search volume, split per platform, co-cited domains, and brand entities. It also explains the cost and free condition, and accepts the ai_trend alternative. The main missing piece is the confirm_quote_id qualifying flow, but it is fully explained in the schema; the agent can still invoke the tool correctly with what is provided.

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 100%, and each parameter (domain, country, confirm_quote_id) is already well-described in JSON schema with its own nuances. The description does not substantially add parameter-level information, such as clarifying the credit/quote logic beyond what the schema already says, so the baseline 3 is appropriate.

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 tool description is very specific: it describes the action ('How often a domain is cited as a source in AI answers') and the resource ('AI Overviews, plus ChatGPT'). It enumerates exactly what will be returned — total mentions, AI search volume, platform split, co-cited domains, and brand entities — and differentiates itself from ai_trend by pointing to ai_trend for monthly history. An agent can immediately distinguish this from the many sibling AI tools.

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 explicitly names an alternative by giving a clear 'Use ai_trend for the month-by-month history' guidance, which tells an agent when not to use this tool. It also gives pricing context and when it is free. However, it does not address other siblings like ai_check, ai_compare, or ai_sources, so a fully-exhaustive when-to-use guide is missing.

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