Diagnose Traffic Drops

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

Beyond the readOnlyHint annotation, the description discloses important behaviors: the window comparison, the categorization logic, and the strict instruction to base analysis only on returned data without speculating. It also instructs the agent to admit when data is insufficient, which is valuable non-obvious behavioral guidance.

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 tightly written and front-loads the core purpose before explaining categories and analytical rules. Every sentence adds useful information, including the important anti-speculation guardrail, with no filler or redundancy.

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 provides the analytical framing, categories, time windows, and reporting constraints, which is strong for a read-only diagnostic tool. However, there is no output schema and the description does not explicitly describe the response shape or fields, so an agent must infer what exact numbers will be returned.

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 75%, with siteUrl, rowLimit, and minClicksDrop already documented in the schema. The description adds no parameter-specific semantics but does not need to because the schema handles most of it. searchType has enum values but no description, and the tool description does not compensate for that gap.

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 opens with a specific verb and resource: 'Find pages that lost traffic and diagnose why.' It then enumerates concrete drop categories (ranking loss, CTR collapse, demand decline), which clearly distinguishes this diagnostic tool from generic analytics or indexing siblings.

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 clearly implies when to use this tool: when diagnosing traffic drops with a 7-day vs 28-day comparison. It does not explicitly name alternative sibling tools or state when not to use it, but the purpose is specific enough that an agent can infer the correct context.

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