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

Beyond annotations (readOnly/idempotent/non-destructive), the description discloses substantial behavior: it reports facts but never secrets (no emails or logins, only short login hashes), option patterns return present+count only without leaking names or values, and filesystem walks are bounded at 5,000 files or 3 seconds per check. It even specifies the fixed summary wording that refuses to declare a site clean. These are exactly the operational details an agent cannot get from the structured fields.

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?

The purpose and the non-leakage guarantees are front-loaded, which is good. However, the body is a single dense run-on paragraph that packs every check into comma-chained clauses, and it is visibly truncated mid-sentence ("per check a…"), which leaves a dangling, unreadable fragment.

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 carries the burden of explaining results and does so: it enumerates each reported field group and states that the response ends with the indicators found plus a fixed summary. Combined with the bounded-walk and no-secrets disclosures, an agent knows what it will receive and how to 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 description coverage is 100% and the schema already documents `since`, `checks`, `site_id`, `plugin_names`, and `option_patterns` in comparable detail, so the baseline is 3. The description adds modest framing by tying `plugin_names`/`option_patterns` to published advisories, but mostly paraphrases what the schema already 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?

The first sentence gives a specific verb+resource+scope: a read-only security check on a suspected-compromised site, followed by an explicit enumeration of every check performed (mu-plugins/drop-ins, unregistered plugin folders, PHP files, plugin modified dates, over-privileged users, admin count, option existence, upgrade leftovers). An agent can tell exactly what it gets back. It never names or contrasts itself with the many sibling security tools (fleet__security_triage, fleet__scan_security, gp_get_security_status), so it falls short of a 5.

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?

The description establishes a clear trigger context ("a site you suspect was compromised") and explains how to use the optional parameters: pass `since` to flag post-date changes, `plugin_names` for published indicator plugin slugs, `option_patterns` for published database indicators. That is strong guidance for a triage workflow. It stops short of stating when NOT to use it or which sibling scan/triage tool to prefer instead.

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