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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial behavior beyond them: a 2-3 day data lag, ~16 months of retained history, the semantics of include_fresh, and exactly what comparison does (previous values, change, and rows that disappeared are listed). This is rich operational context that goes well past the structured fields.

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 purpose, then comparison semantics, then date/history constraints, then the default — a logical ordering. It is dense and slightly long, but nearly every sentence conveys a distinct constraint the agent needs, so little is wasted.

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-parameter, no-output-schema tool with 64% coverage, the description fills the key gaps: comparison behavior, date format, freshness/lag, history window, and defaults. It does not describe the row payload for non-comparison calls or elaborate on the optional site parameter, but overall it is complete enough to invoke correctly.

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 64%, so the description must add meaning, and it does: compare_start_date/compare_end_date have no schema descriptions yet their behavior is fully explained, the YYYY-MM-DD date format is stated, and the grouping dimension usage is illustrated. It does less for site and start_row, but the added meaning around the undocumented comparison params earns above the baseline.

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?

Names a specific verb+resource (Google Search Console performance) and enumerates the exact metrics returned (clicks, impressions, CTR, average position), grouping dimensions, and filter capability, which clearly implies a granular search-analytics tool rather than the sibling overview/opportunities tools. It stops short of explicitly naming which sibling to use instead, so it lands at 4 rather than 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?

Provides useful context such as 'use it for year-over-year and seasonality', the default (last 28 days grouped by query), and the compare_start_date/compare_end_date pattern for period comparison. However, it never states when to prefer this over gsc_performance_overview or gsc_opportunities, nor any exclusions, so guidance is implied rather than explicit.

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