Skip to main content
Glama

List conversations

list_conversations
Read-only

Use this when the user wants to see recent email threads or LinkedIn chats, such as the replies to a campaign. channel is required: email lists the threads of the organization's mailboxes, linkedin the chats of its seats, newest first. Narrow them by folder, campaign, dates and search; an email list also by mailbox and repliesOnly, a LinkedIn list by accountId. For the next page, send the page's next cursor with the same filters. Free. It lists conversations with their latest message, not every message.

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": {
      "channel": "<channel>"
    },
    "name": "list_conversations"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoOnly conversations with a message at or before this ISO 8601 date-time, not before `since`.
sinceNoOnly conversations with a message at or after this ISO 8601 date-time.
cursorNoThe `pagination.nextCursor` of the page before. Later pages keep the first page's size.
folderNoEmail: `inbox` (the default), `sent`, `unread`, `favorite`, `archived`, `spam` or `trash`. LinkedIn: `inbox` (the default, every chat) or `unread`.
searchNoEmail: matches names, addresses, the subject and the text. LinkedIn: matches the other person's name.
channelYes`email` or `linkedin`.
mailboxNoEmail only: one mailbox, or up to 20 separated by commas.
pageSizeNoConversations per page.
accountIdNoLinkedIn only: one seat, by its `id`.
campaignIdNoOnly the conversations of one campaign.
repliesOnlyNoEmail only: true keeps the conversations where the other side wrote back.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover read-only, non-destructive and closed-world; the description adds above that: ordering ("newest first"), cost ("Free."), and the crucial granularity caveat ("lists conversations with their latest message, not every message"). It also discloses the channel-conditional filter matrix, which is real behavioral context rather than restatement.

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-loads the trigger, then channel semantics, then filters, then pagination, then the return-value caveat — a sensible information hierarchy with an unusually dense, low-waste wording. Some sentences are heavily compressed (a single line mixes channel requirement, folder matrix and sort order), which slightly taxes first-pass parsing.

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?

For an 11-parameter tool with no output schema, the description covers the essentials: what entity is listed, what ordering, what each filter scopes, how to paginate, and the fact that only the latest message is included. It doesn't sketch the response shape beyond that caveat, so an agent still learns the full payload only by calling.

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 baseline is 3; the description earns extra by mapping filters to channels ("Narrow them by folder, campaign, dates and search; an email list also by mailbox and repliesOnly, a LinkedIn list by accountId") and by stating the cursor must be paired with the same filters. It stops short of restating defaults or accepted date formats, leaving those to 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?

Opens with a specific user intent ("see recent email threads or LinkedIn chats") and states the concrete resource returned per channel: email lists the threads of the organization's mailboxes, linkedin the chats of its seats. The distinction against the sibling count_conversations/update_conversations is implicit in the verb "list" plus the explicit "it lists conversations... not every message" scoping.

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?

Gives a clear triggering condition ("Use this when the user wants to see recent email threads...such as the replies to a campaign") and operational guidance for paging (reuse the cursor with the same filters). It does not name sibling alternatives such as count_conversations for totals or update_conversations for mutations, so an agent must infer that boundary.

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.

Resources