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

Discloses meaningful behavior beyond annotations: idempotency semantics (returns success even if already read), feature gating requiring the Notification Center feature, and 404 behavior when disabled. These add real context that annotations (idempotentHint, readOnlyHint=false) alone don't convey.

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?

Approximately three dense sentences with no wasted verbiage, front-loaded with the core action. Slightly long but each sentence contributes distinct information (behavior, param semantics, prerequisite).

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?

Complete for a two-parameter mutation tool with no output schema. All salient behavioral aspects (idempotency, feature gating, 404 conditions, parameter semantics) are covered, giving an agent everything needed to call correctly.

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 coverage is 50%, so the description must compensate and does: it explains the semantic meaning of openedFrom values and when to omit it, notably clarifying 'in_app' vs external source channels. The id parameter is adequately documented by the schema.

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 a notification as read for the authenticated user') and distinguishes scope from siblings like markAllNotificationsRead and markNotificationBatchRead by singling out one notification for the authenticated user.

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 clear usage context: when to pass openedFrom ('in_app' vs external link channels) and when to omit it. However, it does not explicitly name alternatives or contrast with markAllNotificationsRead/markNotificationBatchRead for multi-notification cases.

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