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

readOnlyHint=true already establishes that this is a safe read, and the description adds nothing further — no statement about whose notifications are counted (current user vs organization), whether the count is scoped or filtered, or what happens with pagination/limits. For a trivial tool the bar is low, but the description contributes essentially no behavior beyond the annotation.

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?

A single six-word sentence fragment with zero waste and the key qualifier ('unread') up front. It is arguably under-specified rather than verbose, so it does not lose points for length.

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 parameters, no output schema, and readOnlyHint already declared, most of the burden is lifted, but the description never says what shape the answer takes (a bare integer vs an object) or whose notifications are being counted. For a count tool that detail is small but genuinely useful.

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?

The tool takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate. Baseline of 4 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 specific resource and the exact metric being computed (unread notifications), so an agent can tell it apart from list_notifications or mark_notifications_read. It is a noun phrase rather than a verb+resource statement, and no sibling is named explicitly, which keeps it just short of a 5.

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: the agent can infer this is for a badge/indicator rather than for retrieving notification content, but the description never says when to prefer it over list_notifications or how it relates to mark_all_notifications_read. No alternatives or exclusions are stated.

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