Skip to main content
Glama

Read a conversation

get_conversation
Read-only

Read one conversation's transcript by id (from search_conversations), one page at a time, most recent first. Page one is the newest window of messages; pass cursor (the next_cursor from the previous page) to walk backward into older history, a null next_cursor meaning you've reached the start of the conversation. Within each page the messages are in chronological order (oldest→newest) with timestamps, senders and audio transcripts, so a page reads naturally. Optionally bound the range with start_date / end_date — the cursor already carries that range, so you do not re-send the dates when paging. Only conversations the user owns or has been shared are accessible.

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": {
      "id": "<id>"
    },
    "name": "get_conversation"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe conversation id.
limitNoMessages per page, 1–200 (default 100).
cursorNoThe `next_cursor` from a previous page; omit for the first page.
end_dateNoOptional ISO 8601 date (YYYY-MM-DD) upper bound.
start_dateNoOptional ISO 8601 date (YYYY-MM-DD) lower bound.
include_commentsNoInclude the user's comment annotations on messages as `# comment (...)` lines (default false). The cursor carries the choice, so it applies to every page.

Output Schema

NameRequiredDescriptionDefault
idNoThe conversation id this page belongs to.
urlNoWhere a person can open this conversation in Werify.
nameNoThe conversation or group name.
textNoOne page of transcript, oldest→newest within the page, with timestamps, senders and audio transcripts on `> ` continuation lines.
phoneNoThe user's connected number that captures this conversation, the phone the capture tools take; null when no number of theirs captures it.
chat_idNoThis chat on that number, the chat_id the capture tools take; null when phone is null or the number's chat list does not hold it.
metadataNo
next_stepNoPresent only when capture is paused for billing on one of the user's numbers — the transcript still reads, but nothing new is arriving. Relay it to the user.
next_cursorNoPass back as `cursor` to read the window *before* this one. `null` means you have reached the start of the conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/non-destructive annotations, it discloses substantial behavior: access is limited to owned or shared conversations, paging is newest-first with backward cursor walking, a `null` next_cursor signals the start, messages within a page are chronological, and comments are inline-rendered when enabled.

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 the core action and id source, then pagination mechanics, then access caveat. Dense but each sentence carries information; the page-ordering explanation is slightly verbose but justified since it is easy to misinterpret.

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?

Covers access constraints, pagination protocol, date bounding, and comment inclusion, and an output schema exists so return shape need not be described. Nothing an agent needs to page correctly through a transcript 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%, so the baseline is 3, but the description adds real cross-parameter meaning: `cursor` is the prior page's `next_cursor` (null means end), the cursor already carries the date range and include_comments choice so they need not be re-sent, and paging is explicitly backward in time. It adds little about `limit` beyond the schema's default.

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 ('Read one conversation's transcript by id') and names where the id comes from (`search_conversations`), which distinguishes it from sibling list/search tools. An agent can tell exactly what this returns without opening the schema.

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 clear context for use — fetch a transcript for a single conversation id obtained from `search_conversations`, with optional date bounds. It does not explicitly rule out using `search_messages` for cross-conversation or keyword lookups, but the single-id scope implies that distinction.

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