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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: data is Google-finalized with a ~2-3 day lag, days/dates bound every action, compare_periods contrasts with the immediately preceding window, and the tool is FREE with no AI credits. It does not contradict annotations.

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?

The description is compact and front-loaded: the core purpose and metrics appear in the first sentence, followed by data-lag, scoping, and routing guidance. The final cost note is useful but slightly tangential. Every sentence earns its place, though the cost sentence could arguably be trimmed.

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 read-only tool with 10 parameters, 100% schema coverage, an output schema, and strong annotations, the description covers the essential context: data freshness, scoping, cost, and when to use the sibling. It does not enumerate return shapes, but the output schema exists and the description need not explain return values. Minor gap: no explicit mention of pagination or row caps, though the schema covers limit/maxRows.

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 100%, so the schema already documents all 10 parameters thoroughly, including enums and per-action applicability. The description adds a few cross-cutting semantics (days/dates bound every action, compare_periods contrasts with the immediately prior window, cost is FREE) but does not need to repeat parameter details. Baseline 3 is appropriate since the schema carries the heavy lifting.

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?

The description opens with a specific verb ('Read') and resource ('Google Search Console performance'), then enumerates the exact metrics (clicks, impressions, CTR, position) and grouping dimensions (query, page, dimension, period comparison). It also names the sibling tool it is not (gsc_insights) and states the data source is the user's own connected property. This clearly distinguishes it from the 28 sibling tools.

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 description explicitly says when to use this tool vs alternatives: 'For diagnosis (cannibalization, CTR outliers) use gsc_insights rather than recomputing here.' It also states the tool is already scoped to the connected workspace and site, so no domain/site parameter is needed, and notes the ~2-3 day data lag. This gives an agent clear decision criteria for selecting this tool over siblings.

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