traffic_drops

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

The description discloses the classification logic with specific thresholds and warns about speculation. However, with no annotations, it fails to describe other behaviors like read-only nature, rate limits, or output structure. The note about citing site_url and date_range is helpful but partial.

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 efficient, front-loading the main purpose, using bullet points for classifications, and a concise note. Every sentence adds value without 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?

Despite clear purpose, the description is incomplete for a tool with 4 parameters and no output schema. It lacks explanation of parameter effects, return format, and behavior over time (e.g., how days combine). The note about using only returned data is good but insufficient for correct invocation.

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 adds no semantics for the parameters beyond what the schema shows. It mentions site_url and date_range in the note but does not explain the meaning of 'days', 'top_n', or 'min_clicks_prior'. With 0% schema coverage, the description should compensate but does not.

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 identifies 'Pages that lost traffic' and classifies them into three specific types (Ranking-loss, CTR-collapse, Demand-decline) with precise thresholds. This distinguishes it from sibling tools like 'search_analytics' and 'content_decay'.

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 explicitly instructs to 'Use ONLY the data returned by this tool' and warns against speculation, providing clear usage context. However, it does not explicitly compare against alternatives or state when not to use it.

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