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

Goes well beyond the annotations by explaining the conditional side effect: pinned rows are unpinned and kept, while non-pinned rows are removed from the feed. It also discloses feature availability, the 404 result, and the current notification type, matching idempotentHint without contradicting destructiveHint.

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?

Front-loaded with the main purpose and then organized into behavior, constraints, and error condition. Slightly dense with nested clauses, but each sentence earns its place.

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 single-parameter mutation with no output schema, the description covers user scope, exact behavior, idempotency, eligibility, and a relevant 404 condition. Nothing essential to deciding whether and when to invoke it 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 schema already documents the only parameter (id) at 100% coverage. The description does not add parameter-level detail, though it clarifies the object is the user's notification; baseline 3 is appropriate.

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?

Clearly names a specific action and object: dismissing an important notification for the authenticated user. It further disambiguates from generic notification mutations by explaining the Dismiss-button behavior and restricting to important (connection_broken) notifications.

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?

Provides concrete context: only important notifications can be dismissed, the action is scoped to the authenticated user, and it requires the Notification Center feature (404 when disabled). It does not explicitly name alternative tools such as markNotificationRead, so it stops short of full when-to-use routing.

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