compare_periods

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds the implicit default comparison window and the presence of new/lost entities in the result. It omits consequential behavior: that min_impressions (default 10) silently suppresses low-volume entities, how results are ranked/truncated by top_n, and that missing previous_start/previous_end triggers auto-derivation.

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 tight sentence with no filler, and the core behavior plus its default are front-loaded. It is arguably over-compressed for an 11-parameter tool, but nothing in it is wasted.

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?

For an 11-parameter comparison tool with no output schema, the description should say what is measured (clicks, impressions, CTR, position deltas), how rows are ordered and cut off, and how min_impressions affects candidate entities. None of that is present, leaving the agent unable to predict or interpret the response.

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 82%, so the baseline is 3 regardless of the description. The only parameter-level meaning added is the automatic previous-period derivation implied by the parenthetical; top_n and min_impressions remain undocumented in both places, and the description does not explain how dimension interacts with the "new and lost" framing.

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?

"Winners and losers between two periods" conveys a delta/comparison operation, and "with new and lost queries/pages" hints at the output content. But it never says which metrics are compared, and it does not distinguish itself from siblings that also measure change over time (traffic_drops, content_decay, performance_overview), so an agent must guess which tool to reach for.

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 parenthetical "(default: previous equal-length period)" tells the agent what happens when no comparison window is supplied, which is real usage guidance. However there is no when-to-use/when-not-to-use statement and no pointer to the obvious alternatives (performance_query for a single period, traffic_drops for decline diagnosis).

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