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

Goes well beyond the annotations by spelling out exactly what is destroyed versus preserved: a pinned row is unpinned and the card remains, while a non-pinned row is removed from the feed. It also discloses idempotency and the feature-gating failure mode (404 when Notification Center is not enabled for the team).

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?

Information-dense and front-loaded, with the core action stated first and behavioral edge cases following. The pinned/non-pinned clause is long and em-dash heavy, making it slightly harder to parse than necessary, but every sentence carries substantive meaning.

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?

No output schema exists, so the description compensates by covering the meaningful return behaviors (idempotent success, 404 when the feature is disabled) and the full destructive semantics. For a single-parameter mutation with partial annotation coverage, nothing an agent needs to call it correctly 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?

Schema description coverage is 100% for the single 'id' parameter, so the schema already carries the parameter documentation. The description adds no syntax or format detail about the identifier, which is the correct baseline when structured data does the heavy lifting.

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 and resource ('Dismiss an important notification for the authenticated user') and immediately scopes it to important notifications only, which distinguishes it from siblings like markNotificationRead, deleteReadNotifications, and deleteAllNotifications. An agent can identify this tool's distinct role without opening the schema.

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?

It gives an explicit eligibility constraint ('Only important notifications (currently: connection_broken) can be dismissed') and anchors the expected outcome to the product's Dismiss button, which clarifies intent. It never names the sibling alternatives (markNotificationRead, deleteReadNotifications) for non-important notifications, so the when-not-to-use-this routing is left implicit.

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