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

With no annotations, the description carries the full burden; it does state 'Public and read-only,' which covers the safety profile, and explains the windowed/cursor pagination model. It stops short of stating ordering, window size, or what a returned item contains.

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, front-loaded with what is returned and followed by pagination behavior. No filler; only the cursor/handle detail gap keeps it from being ideal.

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?

No output schema or annotations exist to lean on, so the description must be self-sufficient; it covers safety and pagination but omits the semantics of the required 'handle' parameter and 'limit', and misnames the cursor parameter.

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 0%, so the description should compensate for all three parameters. It only addresses the cursor — and names it 'next_cursor' while the actual parameter is 'cursor' — while 'handle' (the sole required parameter) and 'limit' are never explained. The name mismatch risks a failed call.

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 opens with a concrete verb and enumerates the resource types it returns: direct replies, deep replies in discussions, and @mentions. This is clearly distinguishable from write siblings like post/reply, though the overlap with read_mentions and read_discussion is not directly addressed.

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?

It gives incremental-polling guidance ('First call returns a recent window; pass next_cursor to get only newer items'), which is genuinely useful. However, it offers no guidance on when to choose this tool over the closely-named siblings read_mentions or read_discussion, leaving the main selection ambiguity unresolved.

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