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

Annotations already declare readOnlyHint=true, and the description adds useful behavioral context: the operation is scoped to the authenticated user and active organization, requires set_context first, and returns specific fields. This goes beyond the annotation without contradicting it. No rate limits or edge cases are mentioned, but for a read-only list tool the added context is solid.

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?

Three short sentences, each earning its place: the first states purpose and scope, the second covers capabilities, the third states the prerequisite. The most decision-relevant detail (authenticated user, active organization, set_context requirement) is front-loaded.

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?

Despite having no output schema, the description compensates by listing the returned fields (type, title, message, action URL, read status). It also covers the prerequisite context and the available filtering/pagination knobs. An agent has enough to call this tool correctly without further documentation.

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 input schema provides 100% coverage of all three parameters, including defaults and constraints. The description's mention of unread filtering and pagination loosely maps to unreadOnly/skip/take but adds no new parameter-level meaning beyond what the schema already documents. Baseline 3 is appropriate because the schema carries the burden.

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?

Description clearly identifies the verb ('Get'), resource ('notifications'), and scope ('for the authenticated user in the active organization'). It also enumerates the returned fields, making the tool's purpose concrete and distinct from notification-related siblings like get_notification_preferences or mark_notification_read.

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 description gives explicit usage context: it requires organization context and instructs to call set_context first. It also mentions the available filtering and pagination options, which helps an agent know how to shape a call. It does not explicitly name alternatives or state when not to use this tool, but the context is clear enough for typical selection.

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