twist-ai

mark-done

DestructiveIdempotent

Mark threads and conversations as read, unread, archived, or unarchived. Use bulk selectors to clear unread markers for a workspace or channel.

Instructions

Mark threads or conversations as read/unread and archived/unarchived. Individual IDs take priority over bulk selectors whenever both are provided. For threads: markRead=false marks unread, archive=false unarchives; bulk operations (workspaceId/channelId, only used when no ids are given) can also clear all unread. For conversations: can mark as read and archive.

Input Schema

TableJSON Schema

Name	Required	Description
`ids`	No	Specific thread or conversation IDs to mark as done. Use this OR bulk selectors.
`type`	Yes	The type of items to mark as done: thread or conversation.
`archive`	No	Archive items in the inbox (true, default) or unarchive them (false, threads only).
`markRead`	No	Mark items as read (true, default) or unread (false). For threads, false marks the whole thread unread.
`channelId`	No	Mark all threads in this channel as done (threads only).
`clearUnread`	No	Clear all unread markers for workspace (threads only, requires workspaceId, default: false).
`workspaceId`	No	Mark all threads in this workspace as done (threads only).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	Yes
`type`	Yes
`failed`	Yes
`itemType`	Yes
`completed`	Yes
`selectors`	No
`operations`	Yes
`failureCount`	Yes
`successCount`	Yes
`totalRequested`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv7.0.0Sep 21, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations (destructive, idempotent), the description adds critical behavioral details: the priority rule for IDs, the meaning of false values for markRead and archive, and the limitation that bulk operations (workspaceId/channelId) are only used when no IDs are provided. It also clarifies thread vs conversation behavior. This adds substantial value over the annotations.

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?

The description is structured logically: a general statement, then thread-specific details, then conversation details. It is somewhat verbose but each sentence adds useful information. It is front-loaded with the core purpose and then elaborates, which is efficient.

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?

Given the complexity (7 parameters, 1 required, output schema present), the description covers the key behavioral aspects: ID vs bulk priority, boolean semantics, and type-specific operations. It does not describe the output format, but an output schema exists. It does not mention error conditions, but they are not essential for basic usage. Overall, it is complete enough for correct invocation.

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?

While the schema has 100% coverage for parameter descriptions, the description adds semantic meaning beyond the schema: it explains the priority of IDs over bulk selectors, the default true values for archive and markRead, and that bulk operations are only relevant when no IDs are given. This helps agents understand how parameters interact, which is not evident from the schema alone.

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?

The description clearly states the tool's purpose: marking threads or conversations as read/unread and archived/unarchived. It uses a specific verb and resource, and differentiates between the two types. This distinguishes it from siblings like 'reply' or 'update-object'.

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

Usage Guidelines4/5

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

The description provides clear usage context, such as the priority of individual IDs over bulk selectors and when bulk selectors apply (only when no IDs are given). It explains the semantics of the boolean flags. However, it does not explicitly mention alternatives or when not to use this tool, but the context is sufficient for correct selection.

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