keyword_metrics

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

Annotations already declare destructiveHint=false and idempotentHint=true, and the description adds genuinely new context: sandbox mode returns dummy data with no payment, and batching is capped at 1000 keywords per call. It does not explain what happens in production (credit consumption, latency, partial failures) which matters given readOnlyHint=false on an effectively read-only lookup.

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?

Two short sentences, zero filler, with the concrete metrics and batch limit front-loaded and the sandbox caveat isolated in parentheses. Every clause carries information an agent can act on.

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 does the necessary work of enumerating the returned fields (volume, competition, CPC, 12-month history), and the sandbox note prevents misreading dummy values as real data. It stops short of describing result ordering or error behavior when some keywords are rejected, which would complete the picture.

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%, so keywords, language_code and location_code are already well documented in the schema. The description only restates the 1000-keyword cap already encoded as maxItems and adds no meaning about language/location interaction beyond what the schema states, so baseline 3 applies.

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?

States a specific verb and resource ('Google Ads search volume, competition, CPC and 12-month history') with an explicit batch capacity of up to 1000 keywords, and names the upstream provider (DataForSEO Google Ads Search Volume Live). It never names or distinguishes itself from similar siblings such as ai_keyword_demand, keyword_difficulty or search_intent, so an agent must still infer which metrics tool fits.

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 no when-to-use or when-not-to-use guidance and never points to an alternative sibling. The only situational note ('SANDBOX (development): returns dummy data, no payment') describes an environment rather than a usage decision, so keyword-research routing is left entirely to inference.

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