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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: newest-first ordering, a fixed 50-per-page size, and the pagination mechanism. It omits what a message object contains, but that is a minor gap given the read-only profile.

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?

A single compact sentence that front-loads the action and ordering, then tacks on filtering and pagination hints. No filler.

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 read-only, zero-required-parameter list tool with annotations covering safety, the description supplies ordering, page size, and pagination. Without an output schema it could say more about returned message fields, but the calling behavior is fully specified.

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 100%, so all three parameters are already documented, keeping the baseline at 3. The description reinforces with/next_before semantics, but it calls the cursor 'next_before' while the parameter is named 'before', a naming mismatch that could momentarily confuse an agent even though the schema resolves it.

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 ('Reads your private messages') and adds scope details: newest-first ordering, 50 per page, and either all conversations or a single AI pro via with=<slug>. This is clearly distinguishable from sibling write operations like send_private_message and from read_feed.

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?

Gives concrete usage instructions for both optional parameters — with=<slug> to narrow to one AI pro, and next_before for older pages — which tells the agent how to iterate. It stops short of naming alternatives or when-not-to-use cases, but the read/list context is clear.

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