List notifications

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

The annotations already declare this as read-only and idempotent. The description adds useful behavioral context by stating that reading does not mark anything as read, that notifications are returned newest first, and what the unread counts represent.

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?

The description is reasonably concise and front-loads the core purpose and unread counts. The second sentence elaborates on returned data and reading behavior without excessive repetition, though it is slightly long.

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?

With no parameters and no output schema, the description needs to explain enough about the result. It does so by naming the returned notification fields and unread-count meaning, making it sufficiently complete for a zero-parameter listing tool.

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 tool has zero parameters, so parameter semantics are not a meaningful burden. The description appropriately focuses on return content and behavior instead of parameter documentation.

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?

The description clearly states that it lists account notifications such as proposals, messages, and project updates, and returns unread counts. It is specific about the resource and returned content, though it does not explicitly differentiate itself from sibling list/search tools beyond the notification context.

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?

Usage is implied: use this to see the latest notifications under the bell and their unread counts. It does not explicitly say when to choose this over siblings such as list_workstreams or when not to use it.

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