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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses that each check calls paid external AI APIs, imposes a rate limit (5 per 30 minutes per IP), and returns per-AI citation counts. Cost and throttling context like this is exactly what annotations cannot convey.

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?

Three sentences, front-loaded with the purpose, then input constraints, then return shape and cost limit. Nothing is redundant or padding.

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 still explains the return value (per-AI count of questions that cited the domain), plus inputs, limits and cost. Nothing an agent needs to call this correctly 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 100%, so domain and queries are already fully documented. The description restates the 1-5 question bound and the 5-character minimum plus the 'realistic buyer question' framing, which adds only marginal meaning beyond the schema.

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 names a specific verb and resource with scope: it checks whether ChatGPT, Perplexity and Gemini cite a given domain for supplied questions. That is concrete enough to distinguish it from check_ai_crawler_readiness and validate_llms_txt by subject matter, though neither sibling is named explicitly.

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?

It tells the agent what to send ('1 to 5 realistic buyer questions') and states an operational limit of 5 checks per 30 minutes per IP, which shapes invocation. It does not say when to prefer this over the two sibling checks, so there are no explicit exclusions or alternatives.

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