traffic_drops

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuine value by disclosing the output taxonomy and that losses are split into impression loss vs CTR loss, but says nothing about ordering, result limits, cost, or how the comparison window is anchored beyond 'previous period'.

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?

A single dense sentence that front-loads the resource and scope before the diagnostic detail; nothing is redundant. It is jargon-heavy enough that a first-time reader may need a second pass, but every clause conveys 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?

With 10 parameters and no output schema, the description does well to enumerate the diagnostic categories the tool returns, partially substituting for a return-value spec. However, it leaves gaps on result ordering, how min_clicks_prev and top_n interact with the drop ranking, and what the per-drop explanation payload looks like.

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 70%, so most parameters are already documented. The description indirectly explains the purpose of position_threshold (ranking loss) and the demand/min_clicks filtering, but it never addresses top_n, explain_top, dimension, or search_type behavior. Baseline 3 is appropriate when the schema carries most of the burden.

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?

States a specific verb and resource ('pages/queries that lost clicks vs the previous period') plus the diagnostic taxonomy (ranking loss, CTR drop, demand drop, disappeared) and the exact decomposition of click loss. An agent can distinguish this from generic period comparison or performance listing tools without opening the schema.

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 framing as a loss-diagnosis tool implies when to use it, but there is no explicit guidance on when to prefer it over siblings such as compare_periods, content_decay, find_opportunities, or performance_query. No exclusions or prerequisites are stated.

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