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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, which the description reinforces and explains: 'Each call returns only unseen items and marks them seen' accounts for both the write side effect and the non-idempotency in a way the annotations cannot. It omits auth/permission expectations around member_token and does not mention the mark_seen toggle, keeping it from 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?

The delta scope, the response contents, and the scheduling advice are front-loaded in a dense but readable flow with no filler sentences. It is somewhat long for a single paragraph and could split the cadence advice out, but every clause carries information.

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 correctly takes on describing return values and does so thoroughly. The main remaining gap is the undocumented mark_seen parameter, which affects the mutation contract, but for a 2-parameter tool the coverage is otherwise solid.

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 50% (only the rooms array is described), but the description compensates for the nested shape by spelling out rooms=[{room_id, member_token}]. However, the mark_seen boolean parameter is never mentioned despite controlling the central side effect of the tool, so the description adds partial rather than full value.

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 description states a specific verb+resource, 'What's new since you last checked', and enumerates exactly what the response contains: new feed entries (messages, decisions, task changes, notes, joins), pending joins, status, and board version. This is clearly distinguishable from siblings like room_read or room_board, which fetch content rather than a since-last-check delta.

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?

It gives explicit invocation cadence ('call it on a schedule (daily, or hourly for an active project)') and a routing rule for downstream action ('Only bother your human when something needs their decision'). It does not name alternative sibling tools or a when-not-to-use condition, so it falls just short of the top band.

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