List Sites

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

Annotations already declare readOnly/idempotent/openWorld, and the description adds real value beyond them: the hosting server is NOT included by default, sites on revoked servers remain listed as installed but are flagged server_revoked: true under include="server", which prevents misidentifying a stale namesake. It does not discuss pagination timing or response shape, but the schema covers page_size and cursor semantics.

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?

Front-loads the core purpose and return fields, then sequences alternatives→include→filter→revoked-server caveat. Every sentence carries information, though the first sentence is dense and the revoked-server note is a long compound clause that could be tighter.

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 6-param, zero-required list tool with no output schema and full schema coverage, the description covers defaults, filtering, relationship embedding, and a non-obvious edge case (revoked server markers) that an agent would otherwise get wrong. Nothing needed to call it correctly is missing.

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 baseline is 3, and the description layers on concrete usage the schema lacks: filter: {"name": "acme.com"} for single-site lookup and include="server" for relationship embedding. It clarifies default behavior (server omitted unless requested), which the schema's generic include description never states.

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?

States a specific verb and resource (list every site in an organisation across all servers) and enumerates the returned attributes (domain, project type, PHP version, repository, deployment, maintenance-mode state). It distinguishes itself from the server-by-server alternative, so an agent can select it against siblings like list_servers or get_site without opening a 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?

Explicit when-to-use guidance: prefer this over listing sites server by server; use filter by name to find a single site instead of paging; pass include="server" to answer hosting questions in one call. It names the concrete alternative behaviors and the condition selecting each, leaving nothing to inference.

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