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

Annotations already declare non-destructive, idempotent, closed-world behavior, so the safety profile is covered. The description adds the caller-scope restriction (only your own notifications) and, importantly, the return value ('how many were marked') that no output schema supplies.

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, zero waste, with the operation and its scope front-loaded and the return behavior following immediately.

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 no output schema, the description covers what it does, whose notifications are affected, and what comes back. Minor gaps remain (e.g. whether it spans all workspaces or only the current one), but nothing essential to correct invocation 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; baseline 4 applies. The caller-scoped framing is consistent with the empty schema rather than adding conflicting detail.

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+resource ('mark ... notifications as read') with explicit scope ('every unread', 'of the caller's'), which implicitly separates it from the singular sibling mark_notification_read. It does not name that sibling outright, so an agent must infer the bulk-vs-single distinction from the name.

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 phrase 'every unread' implies the bulk-clearing use case, but there is no explicit when-to-use or when-not guidance, and mark_notification_read is never mentioned as the alternative for single items.

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