Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Read the inbox

inbox_read
Read-only

Every conversation people started with the business's own accounts, as People's inbox shows it: comments under its posts and ads, mentions, reviews, direct messages and message requests. Each with who it is from, every message's own words and when, the post a comment is under (its words, address and picture), where it stands (new, drafted, answered by Marsell or by the owner in the platform's own app, yours: the owner's to answer, skipped: the owner chose not to answer it, until they write again, or history: from before the account was connected, or more than two weeks old when Marsell first read it, never answered), the ad or link that brought them when one did, what Marsell read it as, and Marsell's drafted reply. how_it_answers: the last 30 days, counted from these same conversations: the messages that came in and from how many people, how many were answered, the middle and slowest waits for an answer in seconds, and the conversations counted. conversation: one by its id. Reads only.

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": "inbox_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNoThe project's id or exact name. Optional when the account has one project.
conversationNoOne conversation, by its id. Every one when left out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint=false, and destructiveHint=false, so the description's 'Reads only' is consistent. Beyond annotations, the description adds substantial behavioral detail: it enumerates the status values (new, drafted, answered, yours, skipped, history), explains what each means, describes the last-30-days 'how_it_answers' summary, and notes that history includes pre-connection or older-than-two-weeks items. It does not cover pagination, ordering, or rate limits, which keeps it from a 5.

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

Conciseness3/5

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

The description is a single, very dense run-on sentence with nested parentheticals and colon-separated lists. While most details are relevant to understanding the inbox data model, the structure is hard to parse and not front-loaded with a clear action. The content earns its place, but the presentation could be much more concise and organized.

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?

Given two optional parameters, no output schema, and read-only annotations, the description is largely complete: it explains the returned conversation fields, status meanings, and the 'how_it_answers' summary window. It could mention ordering, pagination, or limits, but for an inbox read tool the core information an agent needs is present.

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 description coverage is 100%, so both parameters (project and conversation) are already explained by the schema. The description mentions 'conversation: one by its id', which adds marginal clarity, but it does not extend parameter semantics meaningfully beyond what the schema provides. A baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb+resource: reading conversations in the business's inbox, including comments, mentions, reviews, direct messages, and message requests. It also describes what each conversation contains (sender, messages, post context, status, attribution, drafted reply). It does not explicitly distinguish itself from siblings like conversations_read or waiting_read, so it stops short of a 5.

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?

Usage is implied by the scope statement ('Every conversation people started with the business's own accounts') and by the conversation parameter selecting one by id. There is no explicit when-to-use guidance, no when-not-to-use exclusions, and no named alternative among the many sibling read tools. The agent must infer when this tool is appropriate.

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