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

Although annotations already declare readOnly/idempotent/non-destructive, the description adds substantial context annotations cannot express: per-site caps (50 sites, 50 plugins, 20 patterns), a non-obvious correctness caveat that an empty summary never proves a site is clean, the meaning of `partial`, that no secrets/emails/usernames leave the site, and the receipt_id audit trail. It is fully consistent with readOnlyHint=true ("Changes nothing on the sites").

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?

Almost every clause earns its place, and purpose precedes parameters which precede return shape, so it is front-loaded. However the whole thing is one dense run-on paragraph with no separation between input semantics, output shape and caveats, which makes it hard to scan in a tool-selection context.

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?

There is no output schema, so the description carries the return contract itself: per-site summary, indicators, partial, checks_run/checks_skipped, the detailed report fields, guardpress payload and receipt_id are all enumerated. Combined with parameter semantics and failure behavior, an agent has everything needed to call and interpret it.

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 already 100%, yet the description goes well past it: `since` is explained as flagging changes to plugins/mu-plugins/drop-ins/upgrade leftovers and admin registrations after that date, `plugin_names` as matched against regular, unregistered, must-use and drop-in files, and `option_patterns` as returning presence and count only under a single-`*` prefix/suffix rule. This is meaning the schema does not carry.

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?

Opens with a specific verb, resource and scope: a read-only security check across up to 50 chosen sites returning one combined result, then enumerates exactly what is inspected (plugins, mu-plugins, drop-ins, upgrade folder, users, options, GuardPress). The main gap is that it never distinguishes itself from the near-identical fleet__scan_security or recipe__run_security_sweep siblings, so an agent must infer the boundary from the parameter detail alone.

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?

"For sites you suspect were compromised" supplies a clear triggering condition, and the closing note that sites without the check return errors tells the caller when to expect failure. There is no explicit when-not or named alternative tool, so the routing guidance stops short of the top score.

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