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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds the critical caveat that an empty list on a site with vulnerability_checking off is not a clean bill of health, and notes whether results were validated against a current feed. That is real behavioral context an agent would otherwise get wrong; it stops short of covering cost/latency for fleet-wide calls.

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 core action and source, and every clause carries information. The final sentence runs long with several nested qualifiers, which costs a little readability but nothing is filler.

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 usefully sketches the per-site return shape (severity, fix, patched version, active exploitation, feed freshness). It omits anything about how many sites can be checked at once or expected runtime, but it covers what an agent needs to call and interpret the tool.

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 100% and the single parameter is fully documented there. The description only restates the default scope ('every connected site' vs the schema's 'every eligible site'), which adds marginal meaning rather than syntax or formatting detail.

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+resource (check known vulnerabilities in plugins, themes, and WordPress core) and names the source of truth (GuardPress, falling back to Wordfence or Kadence Security). The phrase 'read now from its security plugin' implicitly separates it from the scan-triggering siblings such as fleet__scan_security.

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?

Covers the default scope ('Optional site_ids, default every connected site'), but never says when to choose this over fleet__scan_security, fleet__security_triage, fleet__list_advisories, or recipe__run_security_sweep. Usage is implied by the verb, not contrasted against alternatives.

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