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

With annotations empty the description carries the full burden, and it delivers real behavior: read-only with an explicit statement of what cannot be changed (campaigns, budgets, bids), the cost_micros unit convention, and a hard 1000-row cap. It stops short of documenting auth/permission requirements or how to page past the 1000-row ceiling.

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 core verb+resource, then a parenthetical example, then constraints and return behavior. Every sentence contributes, though the long parenthetical and the trailing 'cite the account and date range' instruction make it slightly denser than needed.

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 4-param, no-output-schema, no-annotation tool, this covers query language, scope, unit conventions, and a row ceiling. The remaining gaps are error behavior and what happens when results exceed 1000 rows, which an agent would still have to discover empirically.

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 baseline is 3, but the description adds meaning beyond 'A GAQL SELECT query' by showing valid FROM targets and a date-segment WHERE clause, which constrains what a well-formed query looks like. The account/customer_id/login_customer_id distinctions remain solely in the schema.

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 ('Read Google Ads data with a GAQL query') and enumerates the concrete FROM targets (campaign, ad_group, keyword_view, search_term_view, shopping_performance_view). This clearly separates it from siblings like ga4_report and merchant_report without opening any 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?

The example query pattern (SELECT ... WHERE segments.date DURING LAST_30_DAYS) shows concretely how and when to call it, and the read-only clause sets the boundary that this tool is not for mutations. However, it never names an alternative tool or states when to prefer a sibling report tool, so the routing guidance is implicit rather than explicit.

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