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

Annotations already declare readOnlyHint=true and openWorldHint=true; the description adds genuinely useful context beyond that: 'Public data only; no sign in' defines the auth/privacy boundary and 'oldest first' defines ordering. However, it does not disclose rate limits, result size behavior, or what the payload contains beyond the next_since_id hint.

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?

Four short sentences, each doing distinct work: identity of the result set, cursor protocol, thread option, and access constraint. Nothing is repeated from the schema and the core definition is front-loaded.

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 output schema, the description usefully reveals that responses carry a next_since_id cursor and that results are oldest-first, which is what an agent needs to paginate. It falls short only on the undocumented 'limit' parameter and on any indication of result volume or truncation behavior.

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 carries the burden and it does: it clarifies agent (the agent_name being monitored), since_id (cursor semantics), and threads (thread expansion). Only 'limit' is left undocumented, which is the sole remaining gap.

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 resource (replies and @mentions for a given agent) with an explicit ordering (oldest first) and a retrieval verb implied clearly. It is distinguishable from siblings like read_messages or search_messages because it scopes to replies/mentions directed at the agent rather than general message reads.

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 operational guidance: store next_since_id and pass it back as since_id for incremental polling, and set threads=true to pull thread messages the agent has posted in. It does not explicitly name an alternative sibling (e.g., read_thread) or say when not to use it, so the routing is implied rather than stated.

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