nc-mcp-server

list_threads

Read-onlyIdempotent

List the most recently active threads in a Talk conversation by providing the conversation token. Returns thread details including title, reply count, and last activity time.

Instructions

List the most recently active threads in a Talk conversation.

A thread is started by sending a message with a thread_title (see send_message); its ID is the ID of that first message. Read a thread's messages with get_messages(token, thread_id=...).

Args: token: The conversation token. Use list_conversations to find tokens. limit: Maximum number of threads to return (1-50, default 50). Talk only returns the most recently active threads and has no offset.

Returns: JSON with "data" (list of threads, newest activity first) and "pagination" (count, limit, has_more). Each thread has thread_id, token, title, num_replies, last_activity (Unix timestamp), notification_level (default/always/mention/never) and first/last messages as compact lines "[id] author [thread ]: text" (last is null when there are no replies).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`token`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.8.0Sep 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already mark it read-only, idempotent, and non-destructive, and the description adds meaningful behavior: Talk 'returns the most recently active threads and has no offset,' results are ordered newest-first, and edge cases like 'last is null when there are no replies' are disclosed. No contradiction with annotations.

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

Conciseness5/5

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

The description is front-loaded with the core purpose, then uses short labeled sections for background, args, and return shape. Despite its length, each sentence carries functional information and there is no filler.

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?

The description is complete for a list tool: it explains how to obtain the required token, constrains limit, notes lack of offset and ordering, and describes the response structure. Even with an output schema present, the additional return-field detail is valuable rather than missing.

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

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions are absent, but the description compensates fully: token is defined as the conversation token found via list_conversations, and limit gets explicit range (1-50) plus default of 50. Both parameters receive meaning beyond their raw JSON schema types.

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 opens with a specific verb and resource: 'List the most recently active threads in a Talk conversation.' It further clarifies thread identity ('ID is the ID of that first message') and distinguishes itself from related tools like get_thread and list_subscribed_threads by emphasizing recency and conversation scope.

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 gives clear context and routes to related tools: use list_conversations to find tokens, send_message to start a thread, and get_messages to read a thread's contents. It does not explicitly state when to prefer this over list_subscribed_threads or when not to use it, so it stops short of full exclusionary guidance.

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

Deploy Server