Get your notifications (likes, comments, forks, follows, mentions), along with the unread count. Returns cursor-paginated results — use next_cursor from the response for subsequent pages.
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | Cursor for pagination. Omit for the first page, use next_cursor from the previous response for subsequent pages. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral details: it returns unread count and uses cursor-based pagination with next_cursor. This goes beyond what annotations convey, giving agents the mechanics of fetching all results.
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: the first states the purpose and response contents, the second explains pagination. Every sentence contributes essential information without redundancy or filler.
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?
Given there is no output schema, the description must convey what the response includes, and it does: notification types and unread count, plus pagination mechanics. It doesn't enumerate exact fields of a notification object, but for a simple 1-parameter read-only tool, this is adequate.
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?
The input schema already fully describes the cursor parameter, including how to omit it for the first page and use next_cursor for subsequent pages. The description reiterates this pagination flow but does not add additional semantic meaning 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?
The description clearly states the tool retrieves the user's notifications, enumerating specific types (likes, comments, forks, follows, mentions) and includes the unread count. This distinguishes it from sibling tools like mark_notifications_read (which modifies) and get_me (which returns user profile).
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 provides concrete usage guidance for pagination: omit cursor for first page, use next_cursor for subsequent pages. It clearly implies when to use this tool (when notifications are needed) but does not explicitly contrast with alternatives or state exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action, with clear separation between flow lifecycle, execution, model exploration, community, and account tools. Even similar-sounding tools like create_flow, preview_flow, and suggest_flow have clearly different purposes (actually creating, dry-running, and recommending models). Descriptions prevent misselection.
All tools follow a consistent verb_noun pattern in snake_case (e.g., create_flow, list_flows, run_batch, cancel_flow). No mixed conventions or vague verbs like 'process' or 'handle'. The naming is uniform and predictable.
At 33 tools, this is a large surface, but each tool addresses a distinct feature of the cnaps.ai platform, from flow CRUD and execution to community features and notifications. Still, it exceeds the typical well-scoped range and feels heavy, making it a borderline case between appropriate and too many.
The core flow lifecycle (create, read, update, delete, restore, duplicate) and execution (run, batch, cancel) are covered, but structural editing of flow graphs is missing—update_flow only changes parameters, not topology. Additionally, there is no run history, batch list/cancel, or community post update/delete, leaving notable gaps for a platform API.