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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful behavior: the delta is computed against the immediately preceding equal-length window, dates must fall within the data retention window, and each row carries current position/share/sentiment plus a signed delta. It does not mention pagination behavior or result size caps, which is the only notable gap.

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?

Front-loads the ranking definition before the row shape and sort mechanics, and each sentence adds information (comparison window, row granularity, sort semantics, retention constraint, example questions). It runs long and slightly restates the gainers/losers idea, but there is no filler sentence.

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 a 10-parameter read tool with an output schema and full annotation coverage, the description supplies the comparison mechanics, sort semantics, retention constraint, and question routing — enough to call it correctly. The residual gap is undocumented pagination identifiers (limit/offset), which the schema defaults partly cover.

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 only 40% (10 params), so the description carries more burden than usual. It does explain the two tricky params well — sortBy picks which trend delta to rank by, and sortOrder desc = gainers / asc = losers — and clarifies that dates are bounded by retention. But limit, offset, organizationId, projectId, and the date params receive no semantics anywhere, leaving a real coverage 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?

States a specific verb and resource — ranks a project's tracked queries by metric change between adjacent equal-length windows — and defines the row granularity (one engine + country per tracked query). An agent can distinguish this from the sibling time-series tools (get_tracked_query_time_series, get_rank_tracking_time_series) because it is a cross-window comparison, not a series. The sign convention (positive = improved) removes ambiguity about what a 'mover' is.

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?

Gives clear triggering context with example questions ('which queries moved the most', 'my biggest gains and drops versus last period'), which tells the agent when this tool fits. It does not, however, explicitly name an alternative or state when not to use it versus the time-series or search_tracked_queries siblings. Clear usage context without exclusions.

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