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

Annotations already flag destructiveHint=true and non-idempotent, but the description goes further: deactivation preserves the plugin and its settings while delete removes files, delete of an active plugin is refused, and activation failures now return the real reason plus a writability check on wp-config.php and wp-content. That is exactly the operational context annotations cannot encode.

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-loaded with the operation list, then the deactivate-vs-delete distinction, then failure diagnostics. The cache-plugin writability paragraph is the least essential part but still earns its place as an activation troubleshooting note. No filler sentences.

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?

An output schema exists, so return values need not be described, and this description covers mutation consequences, the delete prerequisite, and the activation-failure response. The only real gap is the unexplained `site_url` parameter for multi-site targeting.

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 0%, so the description must carry the load. It documents `plugin` well (file path from wordpress_list_plugins, e.g. "statcounter/statcounter.php") and implicitly enumerates the `action` values in the opening sentence, but `site_url` is never mentioned and the action values are not stated as literal tokens. Partial compensation only.

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 first sentence names four specific operations (activate, deactivate, update, delete) on a well-scoped resource (an already-installed plugin on a connected WordPress site). This cleanly separates it from wordpress_install_plugin and wordpress_list_plugins without needing to open either 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 reasoning is given for the deactivate case (an unused analytics plugin loading scripts on every page), plus a hard prerequisite for delete (an ACTIVE plugin is refused unless you deactivate it first). It also names wordpress_list_plugins as the source of the `plugin` argument, so the caller is routed to the right sibling.

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