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

Annotations already declare readOnlyHint and openWorldHint, but the description adds substantial behavior beyond them: upstream data lag of 2–3 days, silent capping at 500 rows, and error responses returned as a dict with error/message/hint (missing_permission, not_found, rate_limited, auth_error, http_error). It does not describe sorting or ordering of the returned rows.

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 what the tool returns, then walks parameter by parameter; each line earns its place with a concrete rule or error code. It is dense but occasionally telegraphic (e.g. 'page x clicks, impressions, ctr_pct, position'), and the error-dict sentence sits awkwardly between parameter notes.

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 six-parameter read tool, the definition covers semantics, defaults, caps, invalid-input behavior, error payload shape, and the cross-tool escape hatch for pagination. The output schema exists, so the brief mention of returned fields is a bonus rather than a required burden.

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 0%, but the description fully compensates for all six parameters: days semantics with the data-lag adjustment, start_date/end_date format and combined-only rule plus override precedence, search_type with the allowed values (web default, image, video, news, discover, googleNews), limit with the 500 cap, and workspace as an optional slug when only one workspace exists.

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+resource ('Top Landing Pages aus Google-Suche') and enumerates the returned metrics (clicks, impressions, ctr_pct, position), which is enough to distinguish it from sc_top_queries. It never names the sibling it is not, so differentiation from sc_top_queries / sc_performance is left implicit.

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 concrete usage rules: days means the last N days ending today minus 3 (due to 2–3 day data lag), start_date/end_date must be supplied together and override days, and the 500-row cap can only be paged through via sc_performance with start_row. It does not say when to pick this over sc_top_queries or bing_top_pages, so no exclusions/routing for the main ambiguity.

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