Skip to main content
Glama

skein_notifications

Idempotent

Your notification inbox — the bell feed of what happened on the issues and projects you watch. Everything here is per-user: you only ever see and change your own rows. By default a row is a summary, not the change itself: long old/new values are cut to fit the row budget and marked valuesTruncated when they were (see below for where the full value lives).

action="inbox" reads the feed (scope unread | all | archived, cursor-paginated); its first page of unread / all also lists your pending space invitations (no token or link — a person accepts them in the web UI). Only rows of projects you can access now are shown. Four actions clear unread state at four widths — mark_read for one row, mark_read_issue for everything on one issue including its comments, mark_read_card for everything on one Watching card (the issue's own notifications plus its descendants' when you watch it with its subtree — inside and outside the Watching window; answers {"marked": N}), mark_read_all for the whole backlog (optionally scoped to one project). archive moves one row out of the inbox into the archive view; read it back with inbox + scope="archived". Read-only actions: inbox.

Retention: notifications are kept NOTIFICATIONS_RETENTION_DAYS days (90 by default). A background sweep, at least once an hour, deletes a row that is not a mention and is older than that window, read or not, archived or not — EXCEPT a row whose web push is still owed (queued or being delivered): it stays, and is visible in the feed, until the delivery is over. A mention is never deleted, whatever its age.

What an inbox row does NOT carry in full: on a field-change notification the oldValue / newValue pair is cut to fit the row's size budget, and a row whose values were actually cut carries valuesTruncated: true. A row without that key was not cut, so the marker means «there is more», never «this might be all». The two halves of the pair then differ, and the difference decides whether reading on is possible at all. newValue is the entity's CURRENT state, so the route is the entity the row points at: read the issue with skein_show, or, for a comment notification, that comment with skein_comment_get(commentId). oldValue has NO route: the previous value is not on the card (it was overwritten) and no MCP tool returns it — skein_show(includeEvents:true) names the field that changed and who changed it, not what it held before. On that half the truncated preview is all there is; when you need the whole of a long old value, open the issue's activity in the web UI. The row's summary also has the entity reference removed where the row already names the entity, so the same id is not carried twice.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "skein_notifications"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoOnly read by inbox: page size 1..100, default 25.
scopeNoOnly read by inbox: which rows to return — unread (default) | all | archived.unread
actionYesWhat to do: - "inbox" → list your notifications; `scope` picks unread (default), all or archived. - "mark_read" → mark the ONE notification named by `notificationId` as read. - "mark_read_issue" → mark every notification tied to `issueId` read, comments on it included. - "mark_read_card" → mark every notification on the Watching card `issueId` read: the notifications whose card is that issue, its descendants' events included when you watch it with its subtree. - "mark_read_all" → mark every unread notification read; `projectId` narrows the sweep to one project. - "archive" → move the notification named by `notificationId` out of the inbox (sets archived_at and read_at).
cursorNoOnly read by inbox: opaque cursor from the previous page (nextCursor).
issueIdNoFull hierarchical issue id, e.g. "demo-42" or "demo-42.1". Required for mark_read_issue and mark_read_card.
projectIdNoProject UUID. On inbox it narrows the listing to that project; on mark_read_all it narrows the sweep. Optional in both — omit for every project.
notificationIdNoNotification id (positive integer), as returned by inbox. Required for mark_read and archive. Rejected by mark_read_issue, mark_read_card and mark_read_all, which act on more than one row by definition.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say not-read-only, idempotent, non-destructive. The description adds substantial context the annotations cannot: per-user row scoping, the 90-day retention sweep with its mention and pending-push exceptions, truncation behavior with the `valuesTruncated` marker and its one-way meaning, and that archive sets archived_at plus read_at. No contradiction with annotations — the mutation actions are described as state changes, not destructive ones.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded well with the inbox framing and action routing first, but the retention and truncation paragraphs are dense, parenthetical-heavy, and long relative to the core routing message. Every fact is useful, but the phrasing could be tightened without losing meaning — a wall of text for a 6-action tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete on the operationally risky parts: retention data loss window, truncation semantics, per-user scoping, and where full values can be recovered. Lacks any statement of return shape for inbox (row fields, nextCursor naming is only implied via the cursor param) and no output schema exists, so a brief note on what a page contains would have closed the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 earns above that by explaining cross-action parameter applicability that the schema only partially encodes — e.g. that notificationId is rejected by the multi-row actions, and the differing meanings of projectId on inbox vs mark_read_all. It doesn't add syntax detail for cursor, but that is opaque by design.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a concrete metaphor-and-verb framing ('Your notification inbox — the bell feed of what happened on the issues and projects you watch') and then enumerates the six actions with their distinct scopes. An agent can tell this is the per-user notification resource, distinct from skein_show (issue reading) or skein_comment_get, both of which are named as downstream routes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing: which action handles which width of unread-clearing, when to use inbox+scope=archived to read back archived rows, and — critically — which sibling to call to follow a truncated value (skein_show for the issue, skein_comment_get for a comment) and that oldValue has no route at all. Exclusions are stated ('read-only actions: inbox').

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.