mentions

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

No annotations are provided, so description carries the burden. It discloses key behaviors: returns mentions with content, ordering is newest first, and notably 'this is the only reliable read/unread signal in the local store' — a valuable caveat. It doesn't describe pagination, limit behavior, or error conditions, but core behavioral traits are disclosed.

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 compact paragraphs, zero filler. First sentence establishes purpose and ordering, second paragraph covers parameter semantics efficiently. Every sentence earns its place.

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?

Given there's an output schema (so return format doesn't need explanation), no required params, and a modest 4-parameter surface, the description covers the essential ground. It could note limit/pagination semantics and the absence of content filtering, but for a read tool with an output schema this is well-rounded.

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%, and the description compensates well by explaining all three optional parameters (unread_only, days, account) in plain language. It even cross-references list_accounts for the account scoping. It doesn't touch on the 'limit' parameter, but given it has a sensible default (100), that gap is minor.

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 is specific: '@-mentions of you (someone @mentioned you), newest first, with content.' It names the exact verb+resource scope and includes ordering (newest first) and what to expect (content). Distinguishes clearly from siblings like search_messages, recent_messages, and unread_messages.

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?

Description explains what each option does (unread_only, days, account) in the context paragraph. It notes this is 'the only reliable read/unread signal in the local store,' which positions it against the sibling unread_messages tool. However, it doesn't explicitly state when NOT to use it or name alternative tools for when criteria differ.

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