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

Annotations already cover read-only, closed-world, idempotent and non-destructive, so the bar is lower, yet the description adds substantive behavior: the data comes from scheduled checks rather than live site calls, muted problems count toward a warn light, vulnerable components return null when the security plugin isn't checking, and a feed older than a week is marked stale. Those are non-obvious data semantics an agent could not derive from 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 lead clause is front-loaded and every element earns its place — the long field enumeration is justified because no output schema exists. The cost is that it reads as one run-on sentence with nested parentheses around the vulnerability states, which is harder to parse than a short enumerated list would be.

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 return-shape burden and does so thoroughly, including null and stale-feed semantics. What is left implicit is freshness: 'scheduled checks' never says how often those checks run, which matters for interpreting an 'at a glance' health light.

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 site_ids parameter is fully documented in the schema ('Omit for every connected site in the agency'). The description reinforces the per-site default with 'one row per connected site' but adds no format or filtering nuance beyond the schema, so baseline 3 applies.

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 the resource and its scope precisely: a per-site fleet health rollup drawn from scheduled checks, one row per connected site, with an explicit column list (light, alerts, muted count, backup, vulnerable components, WP/PHP versions, SEO audit). It also separates itself from the recipe/* siblings, so an agent can pick it over a detail tool without opening the 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?

It states the boundaries clearly: 'Reads Royally's records only and never calls a site; use the recipe/* tools for detail or a fresh check.' That gives both a when-to-use and a named alternative. It doesn't address the other plausible alternatives (fleet__list_sites, fleet__security_triage, fleet__get_kill_switch_status), so routing against the full sibling set is still partly inferred.

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