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

Annotations already cover the read-only, non-destructive, closed-world profile, yet the description adds real value: sort order, the fields each row carries ('unread', 'readUpTo', mute status, last message), and the permission-refusal behavior for projectKey. It stops short of saying anything about result size or pagination limits for a potentially unbounded list.

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?

Front-loaded with the resource and ordering, and the trailing sentences carry routing and filtering. The dense parentheticals ('title', 'members', who is an administrator) slow scanning somewhat, but no sentence is wasted.

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 compensates by naming the fields returned and the ordering, plus the permission failure mode for the one parameter. An agent has everything needed to call and interpret it correctly.

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 100% and the single projectKey parameter is fully documented in the schema, including the refusal case. The description's 'With projectKey, just that project's chat' largely restates the schema, so the baseline 3 applies.

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 verb and resource ('the chats you are in') and immediately enumerates the chat variants returned: direct, group, project, and agent chats. The ordering rule ('most recently written to first') and the returned metadata make it fully distinguishable from siblings like get_chat_messages and create_chat.

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?

Explicitly routes the agent: 'Read a chat with get_chat_messages; write with send_chat_message', and explains that projectKey narrows to a single project's chat. Use vs. alternative is stated rather than inferred.

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