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

Annotations already declare readOnlyHint/openWorldHint/idempotent/non-destructive, but the description adds what the annotations cannot: each call spends from the agency's own DataForSEO account, the response reports the cost and monthly-limit consumption, and same-day repeats are served from cache at no cost. That is exactly the cost/side-effect disclosure an agent needs before spending money.

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?

Purpose and returned fields are front-loaded in the first two sentences, with cost/caching constraints afterward. Four sentences is proportionate for a metered external API, though the cost discussion occupies nearly half the text and could be tightened.

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 carries the return-value burden and does so by listing the metrics and the total-count field, and it surfaces the billing fields too. It omits what happens when the DataForSEO integration is missing or when a domain has no ranking keywords, which would matter for a metered call.

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% and each parameter (domain, limit, language, location) is documented with format and defaults, so the description adds little parameter-level meaning. It does state result ordering ('best positions first'), but that mildly tension with the schema's limit note ('most searched first'), leaving sort order slightly ambiguous rather than clarified.

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?

Opens with a specific verb+resource ('the keywords a domain ranks for on Google') and enumerates the returned metrics: position, ranking page, search volume, estimated visits, difficulty, plus total keyword count. It also explicitly extends the scope to competitors ('works on any domain'), so an agent can distinguish it from other seo__ tools without reading the schema.

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?

Gives clear situational context: use it on your own domain or a competitor's, and note that a repeat of the same question within a day is free. It stops short of naming alternatives such as seo__rankings, seo__domain_overview or seo__keyword_metrics, so the agent must infer which sibling to pick for a related question.

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