Marks a Backlog watch as read by watch ID to clear unread watch notifications and keep your watch list current.
Mark a watch as read
| Name | Required | Description | Default |
|---|---|---|---|
| watchId | Yes | Watch ID to mark as read |
Changes observed during successful MCP inspections.
v0.15.1v0.13.1v0.11.0Input schema / properties / organizationAdded value: +{
+ "description": "Optional organization name. Use list_organizations to inspect available organizations.",
+ "type": "string"
+}v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, and the description is consistent with that but adds nothing. It does not disclose whether marking read is reversible (via update_watching), whether the watchId must exist or be owned by the caller, or what the response contains. With annotations covering the safety profile, a terse restatement earns little.
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?
A single short, front-loaded sentence with zero padding — nothing needs to be trimmed. It loses a point only because brevity here shades into under-specification rather than disciplined concision.
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 an idempotent mutation tool with no output schema, the description should say what object a watch is, how to obtain a valid watchId, and what state change results. None of that is present, leaving the agent dependent on sibling tools and annotations to infer the operation.
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?
Only one parameter, and schema description coverage is 100% ('Watch ID to mark as read'), so the schema already documents it fully. The description adds no syntax, type, or origin guidance (where to obtain sonar-style watchId) beyond what is structured, so this sits at the baseline.
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?
Specific verb plus resource: 'Mark a watch as read' tells the agent exactly the state transition and the object. However, it offers no differentiation from a close sibling such as mark_notification_as_read, and does not clarify what a 'watch' is (a watching-list item vs. an issue watcher).
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?
There is no statement of when to use this versus mark_notification_as_read or the update_watching path for the same object, and no preconditions (e.g., must the item be unread first?). The agent must infer usage entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.