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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by disclosing pagination behavior, most-recent-first ordering, and type filtering — useful behavioral context an agent needs to consume the result correctly. It doesn't detail cursor mechanics or response shape, but those are minor given the read-only context.

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?

Four sentences, each earning its place: core purpose is front-loaded, then ordering/pagination behavior, then filter semantics with examples, then sibling routing. There is zero filler or repetition of schema/annotation content.

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 read-only, idempotent list tool with no required parameters, the description is largely complete: it covers return behavior (paginated, most-recent first), filtering, and routes to the related count/mark tools. No output schema exists, but the description gives an adequate summary of what is returned. Minor gaps — how pagination continuation works (next cursor) and behavior when workspaceId is omitted — are not critical for correct invocation.

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 0%, so the description must compensate. It does clarify the `type` parameter's purpose with concrete examples (pending_review, credits_exhausted, account_risk, reply_received) and implies `cursor` via 'paginated'. However, `limit` (default 20, max 100) and `workspaceId` are not explained in prose — though the schema's default/minimum/maximum for limit partially self-documents that parameter.

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 ('List'), resource ('notifications'), and scope ('for a workspace'), and adds behavioral specifics ('paginated', 'most-recent first'). It explicitly differentiates from sibling tools by naming count_unread_notifications (count vs. list) and the mark_* tools (mutating vs. read-only), so an agent can select it correctly without opening schemas.

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?

The description explicitly routes to alternatives: 'Use campaignstack_count_unread_notifications to get the unread badge count' and 'Use campaignstack_mark_notification_read or campaignstack_mark_all_notifications_read to mark as read.' This tells the agent when NOT to use this tool, leaving nothing to inference.

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