Skip to main content
Glama
kar-thik

OpenProject CE MCP Server

by kar-thik
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Mark notifications read or unread

mark_notifications
Idempotent

Mark specific notifications as read or unread in one bulk request using notification IDs, so an inbox reflects what has actually been handled.

Instructions

Mark specific notifications read (or unread) in one bulk request.

Use it after you have actually handled what a notification was about, so the user's inbox reflects reality. It is the id-consuming counterpart of list_notifications: pass the row id values from that tool.

Returns {marked, read, ids, message}. OpenProject answers the bulk endpoint with 204 No Content, so marked is the number of ids the call covered — ids that were already in the requested state, or that belong to someone else's inbox, are simply not changed.

Pitfalls. Marking is idempotent, so a retry after a timeout is safe. Pass the notification id, not resource.id — the work package id underneath is a different number entirely. Unknown ids do not fail the call, so do not treat success as proof that every id existed.

Cross-references: get the ids from list_notifications; to clear an entire (optionally filtered) inbox in one go use mark_all_notifications_read.

Input Schema

NameRequiredDescriptionDefault
idsYesNotification ids to mark, e.g. [4711, 4712]. Required and non-empty — this tool never operates on 'everything'. Ids come from list_notifications (the row 'id', not resource.id). At most 200 per call.
readNotrue (default) marks them read; false puts them back in the unread inbox. Both directions are safe here because the ids are explicit.

Output Schema

NameRequiredDescriptionDefault
idsNo
readYes
markedYes
messageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.4.0
    • removedOutput schema / description
      Removed value: -"Outcome of a mark-read/unread call."
    • removedOutput schema / properties / ids / default
      Removed value: -null
    • removedOutput schema / properties / ids / description
      Removed value: -"The notification ids that were marked; null for the filter-based bulk tool."
    • removedOutput schema / properties / marked / description
      Removed value: -"Number of notifications the call covered. For mark_notifications this is the number of ids sent; for mark_all_notifications_read it is how many unread notifications matched the filters when the call ran."
    • removedOutput schema / properties / message / description
      Removed value: -"Human-readable confirmation of what happened."
    • removedOutput schema / properties / read / description
      Removed value: -"True when they were marked read, false when marked unread."
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover safety (readOnly=false, destructive=false, idempotent=true), but the description adds real operational context beyond them: the 204 No Content response means 'marked' is a coverage count, not a success count, so unknown or foreign ids silently no-op. It also flags that marking is idempotent and retry-safe, which is a behavioral guarantee worth restating for a mutation.

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

Conciseness4/5

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

Front-loaded with purpose, then usage, then return shape, then a labeled Pitfalls block and cross-references — good structure for a short reference. Slightly repetitive: the notification-id-versus-resource.id warning appears in both the body and the schema, and the return contract is restated despite an output schema existing.

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

Completeness5/5

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

For a 2-param mutation with an output schema, this is complete: it covers the id-source workflow, the id-type pitfall, silent no-op semantics, idempotency under retry, and where to go for the bulk-clear case. Nothing an agent needs to call it correctly is missing.

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% and already documents both params, so the baseline is 3. The description goes past that by hammering the highest-risk semantic trap — pass the notification id, not resource.id, because the work package id underneath is a different number — and by framing 'read' as both-directions-safe. It stops short of adding anything about the 200-id cap outside the schema.

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?

States a specific verb and resource (mark notifications read/unread), the batch scope ('in one bulk request'), and immediately names the sibling it complements ('the id-consuming counterpart of list_notifications'). An agent can distinguish it from mark_all_notifications_read without opening a schema.

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?

Gives an explicit when ('after you have actually handled what a notification was about') and an explicit alternative ('to clear an entire (optionally filtered) inbox in one go use mark_all_notifications_read'). The workflow dependency on list_notifications as the id source is spelled out.

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

Deploy Server

Other Tools