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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real context on top: Google omits anonymized queries, data lags 2-3 days, results cap at 500 rows, and failures come back as a dict with error/message/hint rather than a list. That is exactly the behavioral detail an agent needs before calling.

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 purpose and the critical summation caveat, then parameter semantics, then error shape; almost no waste. It is dense and closer to a reference block than prose, which costs a little readability.

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?

Covers the caveats, every parameter's semantics, sibling alternatives, limits, and the error contract; the return shape is already defined by the output schema, so nothing needed 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 description coverage is 0%, so the description has to carry parameter meaning, and it does: days means the last N days ending today minus 3, start_date/end_date must be supplied together and override days, search_type accepts web/image/video/news with web as default, limit caps at 500 and is truncated, and workspace is optional when there is only one.

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: top organic search queries with the exact returned fields (query x clicks, impressions, ctr_pct, position). That is clearly distinguishable from sc_top_pages and sc_performance, both of which it names.

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?

Explicitly says not to sum these rows for property totals and routes to sc_performance with dimensions=[] or ['date']. It also says discover/googleNews produce error=unsupported_dimension and that sc_top_pages should be used there, and that pagination goes through sc_performance with start_row.

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