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

Goes well beyond the annotations: explains the operation is additive and non-destructive in effect, starts immediately and runs asynchronously in the background, and describes the response shape (per-site plugin and backup id, plus a list of sites skipped for missing plugin or an in-progress backup). That is exactly the material an agent needs and annotations alone do not supply.

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?

Two dense sentences, front-loaded with the action and target, then defaults, then runtime behavior and response. No filler, though the long second sentence carries several distinct ideas that a reader must parse in one pass.

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 correctly takes on the burden of describing the reply, and it covers the async lifecycle, plugin selection fallback, and the follow-up tool for results. Nothing an agent needs in order to invoke and interpret this tool 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?

Adds defaults absent from the schema (site_ids omitted means every connected site, type defaults to full) and enumerates the three backup scopes in prose, which the schema only exposes as bare enum values. Only the 50-site cap is left implicitly tied to the call rather than the parameter, so not quite a full 5.

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 (start) and resource (backup) plus the mechanism (each site's own plugin, SiteVault with UpdraftPlus fallback) and a scope bound (up to 50 sites). This clearly separates it from siblings like recipe__backup_status, fleet__verify_backup_health and royal-mcp__updraftplus_list_backups.

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?

Explicitly routes the agent to recipe__backup_status for checking finished backups, and the defaults (all connected sites, type full) tell the agent when the call can be made with no arguments. It stops short of naming an alternative to use instead when a backup is already running, only noting that such sites are reported back.

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