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

Annotations already declare readOnly/idempotent/openWorld, and the description adds genuinely non-redundant facts: it fetches each address live from the site (hence multi-second latency), requires the manage_options capability, and returns a 'fix when another plugin' answers a step. It does not describe result shape, but with a rich in-description enumeration of the reported items this is close to complete.

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-loading is good ('Report what else...' first, operational caveats last), but the opening is a single ~130-word run-on sentence with a nested parenthetical list of endpoints and plugins that is hard to parse. The trailing 'Through Royally' line is useful; the middle is dense rather than economical.

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 a complex, annotation-covered tool with no output schema, the description supplies what an agent needs: what categories of findings come back, that URLs are fetched live (slow), the capability required, and that remediation hints are included. Only the exact response structure is unspecified, which is a minor gap.

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?

One optional site_id with a single-value enum and 100% schema description coverage, so the schema already carries its meaning. The description only restates the target site ('site: demo.royalplugins.com') and adds no semantics beyond the schema, which matches the baseline 3.

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 ('Report') and a very specific resource inventory: other MCP servers/hubs, the plugins answering /.well-known/oauth-authorization-server, /.well-known/mcp/server-card.json, /llms.txt and robots.txt, and the AI sign-in path to Royal MCP. No sibling (connection_health, discover_tools, get_tool_info) covers this cross-plugin coexistence/well-known discovery surface, so the agent can tell it apart without opening another 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?

Usage is only implied by the content (auditing MCP exposure or diagnosing an AI app's sign-in path when another plugin interferes). It never says 'use this before/after X' or excludes related siblings like royal_mcp_connection_health or discover_tools. Prerequisites (manage_options, several seconds) are present but they are eligibility, not routing guidance.

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