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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so credit goes to what the description adds: weeks keyed by Monday, incomplete first/last weeks surfaced in partialWeeks, and the exact arithmetic behind sharePointsChange. That is genuine output/edge-case disclosure. Nothing is said about row limits, cost, or pagination for an 11-parameter aggregation.

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 first sentence front-loads the core definition well and the analytical hook follows logically. But the definition sentence is overloaded with parenthetical lists and field names, and the trailing Portuguese restatement duplicates the content without adding information for an English-querying agent.

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-param tool with no output schema, the description usefully sketches the return shape (weekly keys, sharePointsChange, partialWeeks) and the analytical intent. The one real gap is the unresolved default-window disagreement between description (12 weeks) and the days parameter (28), which the agent cannot settle without guessing.

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 100%, so the schema already documents all 11 parameters well; baseline is 3. The description adds only the choice between impressions and clicks as share basis. Worse, it says the default period is 12 weeks while the schema declares days default 28 — that discrepancy is left unresolved and could mislead on the effective window.

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?

Opening clause names the specific resource and grain: weekly share of impressions/clicks per query shape, over the period. It even enumerates the shape buckets and defines the delta field (sharePointsChange), so the agent knows exactly what it gets. It stops short of an explicit contrast with the sibling analyze_query_shapes (snapshot vs. trend), which would have lifted this to a 5.

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?

"Use to see whether questions / conversational queries are growing, i.e. demand shifting toward AI-style searches" gives a concrete analytical trigger. There is no when-not-to-use and no pointer to the nearest alternative (analyze_query_shapes, get_ai_traffic, get_timeseries), so the agent must infer which of these overlapping tools to pick.

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