Skip to main content
Glama

Read a conversation

get_conversation
Read-onlyIdempotent

Returns one conversation of a store: its last 50 messages (from the customer, the chat's assistant or the team) and the open request for the team with its reason, question and summary. Photos, files and phone numbers are left out and email addresses are masked. Each read is recorded in the store's activity log with the app's name. Needs the conversations permission and the store's switch for AI assistants in Settings > Security, and works only for stores the person owns.

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": {
      "store_id": "<store_id>",
      "thread_id": "<thread_id>"
    },
    "name": "get_conversation"
  }
}

Input Schema

NameRequiredDescriptionDefault
store_idYesThe store's store_id (not its name).
thread_idYes

Output Schema

NameRequiredDescriptionDefault
stateNo
channelNo
requestNo
languageNo
left_outNoWhy messages are not listed: older than the last 50, or the system's own notes.
messagesYes
store_idYes
thread_idYes
started_atNo
dashboard_urlNo
messages_left_outNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: a 50-message truncation limit, redaction rules (photos, files and phone numbers omitted, email addresses masked), and the disclosed side effect that each read is logged in the store's activity log under the app's name. Permission and settings gating are also spelled out, so an agent knows exactly what it gets and what it triggers.

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?

Three dense sentences with the payload description front-loaded and constraints after; almost no filler. It runs slightly long by folding redaction, logging and permission details into one paragraph, but each clause carries information an agent needs.

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?

For a two-parameter read tool with an output schema, this covers everything an agent needs: what is returned, what is truncated, what is redacted, what access is required, and what audit side effect occurs. No return-value explanation is required given the output schema, and nothing material is missing.

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

Parameters3/5

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

Schema coverage is only 50%: store_id is documented inline but thread_id is not, and the description never clarifies that thread_id identifies the conversation. It does add meaning for store_id by tying it to stores the person owns and to the AI-assistant switch, which partly compensates, but the undocumented required thread_id leaves a real gap.

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 ('Returns one conversation of a store') and enumerates exactly what comes back: the last 50 messages, their authors (customer, assistant or team), and the open request with reason, question and summary. The word 'one' plus the content list cleanly separates it from list_conversations without needing to name it.

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

Usage Guidelines3/5

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

Gives concrete prerequisites ('Needs the conversations permission and the store's switch for AI assistants in Settings > Security') and an ownership boundary ('works only for stores the person owns'), which tells the agent when a call will fail. It never states when to prefer this over list_conversations or how to obtain a thread_id, so the when-to-use routing is only implied.

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