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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds modest context by framing the result as badge-oriented and restating that it returns a count, but it adds no deeper behavioral nuance such as counting scope or stale-data behavior.

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 description is two short lines with no filler. It front-loads the purpose and adds a returns note, both of which are directly relevant to an agent deciding whether to call this tool.

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 zero-parameter, read-only count tool with rich annotations, the description is nearly complete. It states the purpose, the badge-display use case, and the return value; specifying that the count is an integer would be a minor enhancement.

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, so the description carries little semantic burden. There is nothing about parameters that needs elaboration, and the schema already covers the empty parameter set.

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 uses a specific verb and resource: 'Get the count of unread notifications' for badge display. This clearly distinguishes it from sibling tools like list_notifications, which return notification records, and mark_notification_read, which mutates state.

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?

The parenthetical '(for badge display)' provides clear context for when this count-focused tool should be used. It does not explicitly name alternatives or exclusions, but the zero-parameter count-only design makes the usage context apparent.

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