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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: results are plan-dependent, and on shared hosting per-site traffic does not exist (stats: null, perSite: false). That is exactly the kind of surprise an agent needs pre-warned.

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 core answer is front-loaded in the first sentence, then qualified by plan tier, then examples. It is dense but every clause carries signal; the parenthetical restatement '(stats: null, perSite: false)' is slightly redundant with the preceding sentence.

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?

There is no output schema, and the description compensates by explaining the two possible response shapes and why they differ. A single-parameter read tool needs nothing further to be called 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 100% and the single 'domain' parameter is documented there, so the baseline applies. The phrase 'one of the customer's hosting sites' mildly constrains what domain means (a hosted site, not arbitrary domain), but there is no format or error guidance added.

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?

Opens with a specific verb and resource ('Returns whether the CDN (edge cache) is on...') and enumerates the returned metrics (requests, bandwidth, cache hit rate). An agent can distinguish this from get_my_site_health or get_my_site_runtime without opening the 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?

Gives concrete user phrasings that should route here ('is my CDN on?', 'how much traffic is my site getting?', 'is the cache working?'), which anchors usage well. It does not name a sibling alternative or state when NOT to use it, so it stops short of a 5.

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