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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds the one genuinely non-obvious trait beyond that: the change is irreversible ('no way to mark them unread again'), which materially affects an agent's caution. It does not cover auth requirements or scope boundaries (e.g. all workspaces), keeping it 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 short sentences, front-loaded with the action and followed by the irreversible consequence. No filler and nothing an agent must wade through.

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 mutation with full annotation coverage and no output schema, the description supplies the essential facts: what changes and that it cannot be undone. Only explicit sibling routing 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. The description correctly implies no targeting/filter arguments are needed.

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 ('Mark'), a precisely scoped resource ('every unread notification'), and the resulting state ('as read'). The 'every' scope cleanly distinguishes it from the sibling mark_notification_read, which handles a single notification.

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 implied by the bulk scope: an agent can infer this is the batch variant versus the singular sibling. However, the description never names mark_notification_read or states a condition for choosing between them, so routing is left to inference.

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