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

Annotations already cover readOnly, idempotent, openWorld and non-destructive, so the safety profile is known. The description adds genuinely useful behavior beyond them: the 20-second upper bound, early return when changes arrive, and the instruction to persist the returned cursor. Missing is any statement of what a no-change timeout result looks like, but this is solid context.

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 dense sentences with the primary behavior front-loaded and no filler. The alternative-endpoint note earns its place, though it could be split more cleanly from the core usage instruction.

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 two-parameter, no-output-schema polling tool, the description supplies the timing contract, the cursor lifecycle, and the alternative access path. Nothing an agent needs to invoke it correctly appears to be 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 0%, so the description must compensate. It clarifies that 'after' is a cursor to persist and implies the timeout window, adding real meaning the integer schema does not convey. However, neither parameter's format (e.g., how to obtain the initial cursor, whether timeout_ms is a default or override) is fully documented.

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 (wait for private task changes) plus its core behavior (blocks up to 20s, returns early). It does not differentiate itself from sibling tools like list_notifications or ack_notifications, which an agent polling a task queue would also consider. Clear, but sibling routing is left to inference.

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?

Explicitly gives the alternative for persistent updates (authenticated GET /api/notifications/stream with after cursor) and says browser opening is not needed, which tells the agent when to pick that route instead. It stops short of stating exclusions or when-not-to-use relative to the sibling notification tools.

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