seo_lost_queries

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

Given no annotations, the description fully carries the behavioral burden. It explicitly states the 80% threshold, the minimum click filter, and the data lag warning that can cause false positives. This is thorough and beyond basic expectations.

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?

Three concise sentences with no filler. The first sentence states the main purpose, the second adds a noise filter, and the third warns about data lag. Every sentence adds value.

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 is moderately complex (period comparison, threshold, noise filter). The description explains the logic and output implications but omits parameter details and does not clarify how the periods are defined (e.g., 'previous period' is the same length as 'days' before the current period). With an output schema present, the return values are handled, but parameter semantics are missing.

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 input schema has 0% description coverage, and the description does not mention any parameters (site, days). It provides no additional meaning to help the agent understand how to set the parameters correctly.

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 it finds queries with 80%+ fewer clicks compared to a previous period, specifying a specific resource (queries) and a clear action (find lost queries). It distinguishes from sibling tools like traffic_drops by focusing on query-level drops.

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 context on when results are meaningful (at least 5 clicks in previous period) and warns about incomplete data in the last 2-3 days. However, it does not explicitly compare to sibling tools or specify when to prefer this over alternatives.

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