aism_plugin_action

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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds substantial context beyond them: the required capability for delete, the inactive-plugin precondition, the fact that updates pull the WordPress-advertised package, and the self-management and multisite exclusions. It stops short of saying whether a failed delete leaves state changed or what the failure surface looks like.

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?

Three short sentences, front-loaded with the action set, then constraints, then exclusions. Every sentence carries distinct information; nothing is repeated from annotations or schema.

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 an unannotated-output mutation tool, the description covers permissions and preconditions well, but leaves the plugin identifier format undefined and gives no sense of the success/error outcome. That leaves an agent able to decide to call it but not necessarily to call it correctly on the first try.

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 description coverage is only 33% — `site` is documented but `plugin` is a bare minLength-1 string with no hint of the expected format (slug, directory name, or plugin file path), which is the single most important thing to get right. The description adds no parameter-level meaning at all, so with low coverage it fails to compensate.

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 names a specific resource (installed plugin) and enumerates the four supported operations (activate/deactivate/update/delete), so the agent knows exactly what class of action this is. It does not, however, distinguish this tool's 'update' action from the sibling aism_plugin_update, leaving a real ambiguity among siblings.

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 gives concrete preconditions: deletion needs the plugins:delete capability and the plugin must already be inactive, and it states that AI Site Manager cannot manage itself and multisite mutations are unavailable. What it lacks is routing guidance against aism_plugin_install/aism_plugin_update, so the agent must still guess which mutation tool to pick.

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