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

The description mentions the 15-credit cost, which is a side effect, but it contradicts the annotations: destructiveHint is true and readOnlyHint is false, yet the tool is described as a data lookup. There is no disclosure of any destructive action or non-read-only behavior, so the description directly contradicts the annotation set. This is a serious inconsistency.

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 two concise sentences with no redundancy. The primary purpose is stated first, and the credit cost is a valuable extra detail. Every word earns its place.

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?

The tool has 5 parameters and no output schema, yet the description does not clarify the return format (e.g., per-keyword objects, aggregate metrics). It also fails to reconcile the contradictory annotations. For a moderately complex batch tool, this is incomplete; an agent would need more detail on response structure and the meaning of the boolean flags.

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 descriptions cover 60% of parameters (keywords, language_name, location_name), providing some meaning. However, the description itself adds no parameter-level details, and the boolean parameters (search_partners, include_monthly_searches) are undocumented in both the schema and the description. With coverage in the mid-range, the description does not compensate for the missing guidance on these flags.

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 clearly states the tool's function: retrieving Google Ads keyword search volume, CPC, and competition for a batch of keywords. This is specific and distinct from sibling tools like find_keyword_ideas or get_ranked_keywords, which focus on idea generation or ranking data. The verb 'get' is implied, and the resource is explicitly named.

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 provides no guidance on when to use this tool versus alternatives. It does not mention scenarios like 'when you need volume/CPC metrics' or compare with find_keyword_ideas or search_serp. The agent must infer the appropriate context from the tool's purpose alone, which is insufficient.

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