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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the description's job is to explain mechanics. It does: three consecutive windows, default 28 days each for 84 days total, strict 'fell in every window' semantics, and output ordered by clicks lost — behavior an agent could not infer from the schema or annotations.

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 short sentences, zero filler: definition and window math first, ordering second, use case last. Every clause carries information and the key constraint (fell in every one of 3 windows) is front-loaded.

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 read-only annotations, seven parameters, and no output schema, the definition supplies enough to call the tool correctly: what qualifies, how the window length is chosen, and how results are sorted. The only gap is that it does not describe the per-page fields returned (or pagination via limit), which the agent will discover only at call time.

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 coverage is 86%, so the baseline is 3; the description goes beyond it by explaining that the window length derives from the chosen period and that there are three consecutive windows totaling the span, which is essential for interpreting range/start_date/end_date and min_drop_pct together. It does not spell out the exact derivation of window boundaries from start_date/end_date, leaving that step inferential.

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 names the specific population (pages whose clicks fell in all of the last 3 consecutive windows) and the outcome (candidates for refresh), which is far more concrete than the title alone. It implicitly separates itself from a one-off-dip tool by saying 'a steady slide, not a one-off dip,' but it never names the sibling (report_traffic_drops), so the differentiation is left to inference.

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?

Usage is present only as an implied framing: 'Candidates for a content refresh' tells the agent what to do with results, and the 'steady slide, not a one-off dip' phrasing hints at when this beats a generic drop report. There is no explicit statement of when to use this versus report_traffic_drops or report_quick_wins, and no exclusions or prerequisites.

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