Get notifications

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

With no annotations, the description carries the burden and does well: it discloses the non-destructive, read-only nature ('never marks anything read') and names the return fields (`all_chats`, `this_chat`, `other_chats`). It stops short of describing limits, pagination, or ordering of the returned chats.

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 core purpose, then the chat_id split, then the read_inbox alternative. Dense but nearly every clause carries information; the final sentence about other tools' `new_since_last_read` is useful but slightly tangential.

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?

There is no output schema, so the description must explain the shape of the response, and it does name the key buckets and what they count. Minor gap: no mention of limits, ordering, or how many chats are returned.

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%, so the baseline is 3. The description reinforces chat_id's partitioning effect but adds no new semantics for `channel` or `connection_id` beyond what the schema already documents.

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+resource and scope: what arrived from the other side since chats were last read, with totals (`all_chats`) and per-chat message/reaction counts. It clearly distinguishes itself from read_inbox, which actually reads.

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 names the alternative and its condition: 'Never marks anything read; read_inbox with a chat_id reads one.' It also explains the chat_id split behavior, so an agent knows both when to use this tool and when to switch.

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