Get keyword metrics

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

With annotations only declaring readOnlyHint=false and openWorldHint=true, the description carries the important behavioral load and does so well: write-scope requirement, budget spent from the project's own DataForSEO account, best-effort cost ceiling, 700-keyword batch limit, 12-hour cache shared with API and UI, and clickstream doubling cost. These are exactly the non-obvious traits 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?

Five dense sentences, no filler, and the cost-control workflow is front-loaded after the auth note. It is efficient but skips over the fundamental 'what does this return' sentence, so the structure is optimized for cost rather than selection.

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?

There is no output schema, yet the description never says what metrics come back or in what shape, which is a notable gap for a metrics-lookup tool. Cost, auth, batching, and caching are covered thoroughly, so the agent can invoke it safely but cannot predict the result.

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 71%, so the schema does much of the work, but the description adds real semantics: estimate_only is a free dry run that does not call the provider, max_cost_cents is a best-effort guard, and include_clickstream doubles cost. It leaves 'fresh' and 'connection_id' unaddressed, and the 700-keyword note merely repeats the schema's maxItems.

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 never actually states what the tool does — it never says it fetches search volume/CPC/difficulty metrics for a set of keywords. All content is operational (auth scope, cost model, caching), leaving the agent to infer the verb+resource from the name and title alone. It is contextual but not purpose-defining.

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?

Clear procedural guidance: call with estimate_only first for a free dry run, then use max_cost_cents as a guard, and consult get_provider_rates for the rate card. It does not, however, contrast this tool against close siblings like research_keywords, estimate_keyword_research_cost, get_keyword, or list_keywords, so the agent still has to guess which is appropriate.

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