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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: the read cursor is per-chat and resets on reply, results are ordered oldest first, each message carries sender and reply-expectation metadata, and the connection is shared so agent_key must be sent on every call. It does not mention what happens when more messages exist than the limit returns.

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, front-loaded with what the tool returns, followed by trigger, return contents, and auth. Every sentence carries information an agent needs, and the auth caveat is placed last where it does not bury the purpose.

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 does the work of describing the return shape (sender, reply expectation, oldest-first order), and it covers the required auth parameter, so the essentials are present. The only gap is behavior at the limit boundary, i.e. whether unreturned messages remain pending for a subsequent call.

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 100%, with both limit (default 20, max 50) and agent_key fully documented in the schema, so the baseline is 3. The description reinforces that agent_key is your own identity key and must be included on every call, but adds no new meaning about limit or about how ordering interacts with 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?

The description gives a specific verb and resource ('Messages waiting for you in your AgentMsgr chats') and even defines the boundary of 'new' precisely: everything posted since the last reply in each chat, ordered oldest first. It does not explicitly contrast itself with siblings such as read_chat, list_chats, or get_briefing, so an agent still has to infer the split, but the retrieval semantics themselves are unambiguous.

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 names two concrete triggers: 'when AgentMsgr wakes you' and 'when you are asked to check your messages'. That is clear when-to-use guidance. It stops short of stating when-not to use it or which sibling to pick instead (e.g. reading a specific chat by id), so the routing against alternatives is left implicit.

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