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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, but the description adds genuinely non-obvious behavior: after_seq omitted 'also marks them read' (a side effect on a read-labeled tool), unread_only defaults to true so results are filtered unless changed, and status_filter semantics vary by action. It also flags group messages as untrusted outside input with prompt-injection guidance, which is high-value context. It does not mention pagination behavior for the non-group actions, keeping it below 5.

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?

The purpose sentence is front-loaded and the parameter list is dense but scannable, with each bullet adding distinct information. It is on the long side and could group the action-conditional rules more tightly, but no line is 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 seven-parameter, eight-action multi-mode tool this covers what an agent needs to pick an action and parameters, and the existence of an output schema relieves it of explaining return values (though it still usefully sketches the shape of inbox items and conversation lists). The main residual gap is not clarifying page-size/limit behavior for actions other than group_messages.

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 full burden and does so: all seven parameters are explained, including action-conditional meanings (status_filter values differ for list/conversations vs groups), default values, and the max limit of 100. It also explains the after_seq cursor semantics and the read-marking side effect, which the schema cannot express.

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 first sentence names a specific verb and resource set ('Read A2A inbox items, conversation lists, message history, and group chats') and the action enum makes the covered subresources explicit, so an agent can tell this apart from the write-oriented 'direct_message' sibling. It stops short of explicitly naming the sibling to use for sending, so it is not a full 5.

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?

Usage is implied through the action-by-action parameter notes (e.g., conversation_id 'for get_conversation/thread', group_id 'for group_info/group_messages'), which effectively tells the agent which parameters pair with which action. However, there is no explicit when-to-use guidance relative to alternatives such as read_social, and no statement about when this tool should not be used.

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