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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description usefully adds that each chat carries an unread_count and that shared-project history is excluded. It does not mention ordering, pagination, or whether the list is complete or limited, which keeps it below a 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?

Two sentences, front-loaded with what the tool returns and the scoping constraint, then a compact routing clause. No filler or restated name.

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?

No output schema exists, and the description covers the essential return attribute (unread_count per chat) plus scope exclusions, which is enough to call it correctly. Ordering and result-size behavior remain unspecified.

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?

Zero parameters, so the baseline is 4. The description's mention of unread_count describes returned content rather than adding parameter meaning, but nothing is missing.

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 (list AccountHub one-to-one chats) and narrows scope inline: private two-person conversations, separate from shared project histories, no prior history imported. It also names the sibling alternatives, so an agent can distinguish it from list_unread_chats or read_direct_chat without opening any schema.

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 each adjacent intent: send_chat_message for sending, read_chat for reading one, list_unread_chats for unread across one-to-one AND group chats. That is a clear when-to-use-this vs when-to-use-alternatives statement.

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