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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial behavior beyond them: the not_applicable shared-hosting outcome, the meaning of agentReporting=false (server not confirmed healthy, just unobservable), and the rule to only mention upgrading when upgradeSuggested is true. That is exactly the kind of interpretation guidance annotations cannot convey.

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?

Purpose and scope are front-loaded in the first sentence, followed by usage triggers, alternatives, and output-handling rules in a logical order with no filler. It is on the long side because of the output narration instructions, but each sentence carries actionable content rather than padding.

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?

No output schema exists, so the description correctly compensates by naming the key return fields (`summary`, `findings`, `agentReporting`, `upgradeSuggested`) and prescribing how to present them. Combined with the plan-scoped diagnostics and hosting-type caveat, an agent has everything needed to call and interpret the result.

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?

There is a single optional parameter at 100% schema description coverage, so the schema already explains `domain` as the site to diagnose. The description adds only the mild constraint that it is optional when the customer has exactly one site, which is essentially a restatement. Baseline 3 is appropriate.

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 and resource (diagnoses performance of the customer's own VPS) plus the exact signal domains it covers: CPU load vs. plan vCPU count, memory pressure, disk fullness. It explicitly distinguishes itself from check_uptime (reachability) and get_my_site_health (history), so an agent can route without opening a 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?

Gives concrete trigger phrasings ("why is my site slow?", "do I need a bigger plan?") and explicit exclusions with named alternatives for reachability and uptime history. It also states the shared-hosting case returns not_applicable and instructs the agent to say so rather than guess.

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