Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Conversations read

conversations_read
Read-only

The person's own conversations with you in this project, from every place they talk to you (the web app, Telegram, Slack, their own AI). With nothing given, lists them, the latest first, each with its id, name, place, when it was last active and a short summary. With words, finds the messages that say them, in which conversation and when. With conversation (an id from the list), reads that conversation's messages whole. It reads only this person's own conversations and changes nothing.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "conversations_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
wordsNowords to find in the conversations
projectNoThe project's id or exact name. Optional when the account has one project.
conversationNoa conversation's id, from the list, to read its messages whole

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, yet the description still adds substantive behavior: list results are ordered latest-first and include id, name, place, last-active time and a short summary; search returns matching messages with their conversation and timestamp; a conversation read returns messages whole. The scoping constraint ('only this person's own conversations') adds a data-access boundary the annotations do not capture.

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?

Four sentences, front-loaded with the resource and scope, then the three modes in the order an agent would try them. Nearly every clause carries information. Minor redundancy: 'changes nothing' restates readOnlyHint=false and the destructive hint already provided by annotations.

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?

There is no output schema, so the description carries the burden of describing return values, and it does so per mode (fields listed, search hits with conversation and time, full message bodies). Combined with the scope and safety statements, an agent has everything needed to pick the right mode and interpret results.

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 description coverage is 100%, so the schema already documents all three parameters and the baseline is 3. The description goes further by explaining what each mode yields for each parameter, especially that 'conversation' must be an id from the list and that 'words' matches message text rather than conversation names. 'project' is only implicitly covered by 'in this project', which is the one small 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?

The description names a specific resource (the person's own conversations across web app, Telegram, Slack, their own AI) and a specific verb (reads), then enumerates three distinct modes of operation keyed to which parameters are supplied. An agent can tell immediately this is a read-only conversation retrieval tool with list, search, and full-read behaviors, distinct from siblings like memory_search or inbox_read.

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?

Mode selection is spelled out explicitly and tied to parameters: 'With nothing given' lists, 'With words' searches message text, 'With conversation' reads a thread whole. That is unusually clear when-to-use guidance. It stops short of naming a sibling alternative or an explicit when-not case beyond the scope note that it reads only this person's own conversations.

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

All Marsell toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources