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

Annotations only carry destructiveHint=false and a title, so the description carries the burden and does so well: it discloses the visible effect (bold plus a dot until opened), the privacy scope (nobody else sees it), and the counter-intuitive interaction with unread counting. That is exactly the behavioral context annotations can't express.

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 the action and scope, followed by the caveat. No filler, no restatement of the tool 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?

For a one-parameter, low-risk, self-scoped mutation with no output schema, the description covers action, effect, privacy, and the counting caveat — everything an agent needs to call 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 chat_id parameter already documents its origin (from list_unread_chats / read_chat). The description adds no format or sourcing detail beyond the schema, so the baseline of 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 (mark unread) and resource (one AccountHub chat), and explicitly enumerates the valid chat kinds — one-to-one or group/shared project. An agent can distinguish it from read_chat, list_unread_chats and the many message-mutation siblings 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?

Gives the operative context: this is a personal reminder only, and list_unread_chats will not reflect it — the single most important routing caveat. It stops short of an explicit when-not-to-use statement (e.g. use a message alert or notification instead when others must see it), so it is strong but not complete.

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