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

Annotations already cover the read-only, non-destructive, open-world profile, and the description adds real value beyond them: it discloses the precondition that only connections opened to agents are readable, and warns that breakdown rows will not sum to the site totals. That totals-vs-rows caveat and the 'period and notes say what was actually counted' sentence give the agent interpretive context it could not get from 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?

Three sentences, front-loaded with purpose, followed by provider detail and then the interpretive caveat. The provider enumeration is dense but each clause carries distinct information; there is little filler, though the provider list is long enough to slightly dilute the front-loading.

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 seven-parameter read-only tool with no output schema, the description covers what metrics are returned, what dimensions are available per provider, the auth prerequisite, and the totals caveat. What it does not state — row ordering, pagination beyond the schema's limit — is either in the schema or minor for a read call.

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 earns more by mapping which breakdown values work with which provider (e.g. query is Search Console's dimension, channel and landing page belong to Google Analytics 4, referrer and source to Vercel). That cross-provider mapping of the 'by' parameter is not in the schema and prevents invalid combinations.

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 names a specific verb-and-resource pair (how a project's website was visited, from the counting service) and enumerates the three providers plus their metrics and dimensions, so an agent knows exactly what data comes back. It stops short of naming sibling analytics tools (admin_funnel, admin_landing_week, admin_overview), so differentiation relies on the provider framing rather than explicit contrast.

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?

There is implied guidance: 'Only connections opened to agents are read' and 'Omit for totals only' tell the agent when breakdowns apply, and the 'site' param says to omit it when only one site is open. But there is no explicit when-to-use or when-not-to-use statement relative to the admin_* analytics siblings, leaving the alternative selection to inference.

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