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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds valuable behavioral context: the synchronous nature, the DataForSEO envelope with data in tasks[0].result and status_code, and the critical note that a rejected request still returns HTTP 200. This exceeds what annotations provide and warns the agent about response handling.

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 dense but efficient, front-loading the core purpose and then providing operational details (size, cost, envelope). Each sentence adds value; no filler. The length is justified by the amount of critical operational information.

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 description thoroughly covers output envelope and cost/depth trade-offs, and the output schema handles return values. However, it omits input structure entirely, fails to reconcile the 'keyword' mention with the actual schema fields, and does not explain the anyOf requirement. For a tool with nested array input and multiple optional fields, this is a significant gap.

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?

The description says 'keyword' but the schema requires either advertiser_ids or target (domain), creating confusion. It provides no explanation of the body array structure, the anyOf constraint, or how to specify location. With schema description coverage reported as 0%, the description fails to compensate for parameter meaning, leaving the agent without guidance on how to construct valid input.

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: 'Returns the ads running against a keyword on Google, synchronously.' It specifies the verb (returns), resource (ads), and context (keyword on Google). This distinguishes it from the many sibling tools that return other SERP types (organic, images, etc.) and from the advertiser-focused tool.

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 detailed guidance on choosing among the three result depths (regular, advanced, html) and notes this family is the cheapest source of search data. However, it does not explicitly compare against alternative tools (e.g., advertiser_live) or state when to use this tool vs. others, only intra-tool depth selection.

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