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

Annotations already establish readOnly/idempotent/non-destructive, but the description adds genuinely useful behavior: Search Console data 'runs two to three days behind,' and the failure states 'connected: false' / 'needsReconnect' plus the 'connectUrl' to reconnect. That auth/connection context is real value beyond the annotations. It omits any error handling or rate/pagination limits, keeping it at 4.

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?

A single dense paragraph, front-loaded with the primary metrics before drilling into topPages and strikingDistance. Nearly every clause carries information an agent needs, especially given there is no output schema. It is on the long side and the parenthetical `range`/`previousRange` aside interrupts flow, so not a 5.

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?

With no output schema, the description carries the burden of explaining returns, and it does so thoroughly: metric set, 28-day-vs-prior-28-day comparison, topPages, strikingDistance thresholds, and disconnection states. It is nearly complete, only leaving the siteId parameter and the ambiguous range/previousRange references unaddressed.

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 67%, above the midpoint, and the schema already documents pages (default 10) and queries (default 15). The description links these to outputs ('topPages', 'strikingDistance' queries ranking 11-20 with >=10 impressions), adding meaning, but siteId is undocumented in both schema and description, and the referenced `range`/`previousRange` do not appear in the input schema, which is mildly confusing.

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 concretely names the resource and scope: 'The site's Google search numbers from its connected Search Console: clicks, impressions, click-through rate and average position.' That is far more specific than the name alone and separates it from sibling tools like findings_list or link_suggestions, which are about fixes/links rather than analytics. It stops short of a crisp verb-led statement or an explicit sibling comparison, so a 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?

Usage is only implied: an agent infers it should call this when it needs Search Console metrics. There is no explicit 'use this when…' statement, no when-not guidance, and no named alternative (e.g. versus focus_page or sites_list). The surrounding detail describes content, not selection criteria.

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