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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds real behavioral context beyond that: the PLATO site-wide messaging disablement means this counts notifications only, not conversation messages — a domain fact an agent could not infer. It does not discuss freshness or polling cost beyond 'cheaper', keeping it just short of a 5.

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?

Two sentences, front-loaded with the action and the cost/alternative comparison, with the caveat second. No redundant restatement of the name or annotations.

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?

Zero parameters, an output schema covering the return value, and annotations covering safety — the description fills the remaining gap with the sibling routing and the messaging-disabled caveat. Nothing needed to call it correctly is missing.

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?

Zero parameters, so there is no parameter semantics to explain; the baseline applies. The description correctly implies no filtering arguments are needed by framing it as a simple account-level count.

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?

Specific verb and resource ('Get a count of this account's unread notifications') with explicit scope ('this account's'). It is clearly distinguished from the sibling get_unread_messages by contrasting count-only vs. content.

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?

Names the alternative (get_unread_messages) and the condition that should send the agent there ('when you don't need the content'), plus a cost rationale ('a cheaper check'). The note about messaging being disabled clarifies that a message-count tool is not the substitute here.

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