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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the description correctly spends its budget on non-obvious behavior: Pacific-time day boundaries, Google's 2-3 day fill-in latency causing recent days to grow, topQueries being truncated relative to totals, countsFrom/hasData semantics, and plan gating. There is no return schema, and these caveats are exactly what an agent would otherwise misreport.

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-loaded with the selection rule, then a compact bullet list of return fields — efficient given there is no output schema. Minor waste exists: '180d, 365d, and all need Pro or MAX, as the other long periods do' restates the schema's plan note in an awkward clause.

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?

Two-parameter, no-output-schema tool whose description fully covers return shape, unit conventions (ctr 0-1, position 1 is top), time zone, data latency, and the empty-data case. Nothing an agent needs to call and interpret the result correctly is missing.

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% and the parameter descriptions already cover period defaults and plan gating, so the baseline is 3. The description still adds real meaning: siteId is a page whose Search data is read at its Convika URL path, custom domains are excluded, and the period windows have latency caveats that affect interpretation.

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 (Google Search performance for one page): clicks, impressions, CTR, average position, and top queries. It explicitly separates itself from get_analytics_summary ('Not a page view or a visitor'), so an agent can choose between the two analytics tools without opening either 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?

Opens with an explicit when-to-use clause tied to user phrasing (including Japanese example queries like 「検索順位は？」), and closes with an explicit when-not ('Not a page view or a visitor in get_analytics_summary'). Plan prerequisites (180d/365d/all need Pro or MAX) and scope limits (custom domains not covered) are also stated.

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