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

Beyond the annotations, it discloses that no undo point is recorded (consistent with destructiveHint=true), that the site gets its own tables, that the admin must be an existing user, and that WordPress strips disallowed characters and refuses duplicates. It even reports the return fields (created, blog_id, url) and the connection's forwarding scope.

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?

It is a single dense paragraph with the core action front-loaded, followed by return values, prerequisites, and validation. Every clause carries information, though the forwarding note at the end could be positioned earlier for better scanning.

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 destructive, non-idempotent mutation with no output schema, the description covers prerequisites, validation failures, return values, irreversibility, and scope. An agent has everything needed to decide and invoke it 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?

With 100% schema coverage, the schema already documents all four parameters, so the baseline is 3. The description adds genuine meaning by framing ownership ('owned by an existing user') and the refusal on unknown admin_email, which reinforces the schema's admin_email semantics rather than merely restating them.

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 uses a specific verb+resource combination ('create a new site in the network') and immediately scopes it to multisite with its own tables, distinguishing it from siblings like wp_network_list_sites and connect_add_site. An agent can tell this is a network-level site provisioning tool, not a content or settings tool.

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?

It clearly states prerequisites (a multisite network and a network super admin) and the validation behavior ('refuses an empty or already taken address'), which tells the agent when the call will succeed or fail. It does not explicitly name alternatives or exclusions among the ~90 siblings, but the multisite framing makes the context unambiguous.

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