Skip to main content
Glama
Sign In

Moatless

by store.moatless
OverviewDiscussionsAdmin

List my conversations

my_conversations
Read-only

The signed-in user's conversations with other people on Moatless, most recent first: who each one is with (other_handle), its newest message, when it was sent, and whether the user has messages in it they haven't read on the website (unread?).

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": {
      "context": "<context>"
    },
    "name": "my_conversations"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
limitNoThe maximum number of records to return
filterNoA filter to apply to the query: either a condition {"field": ..., "operator": ..., "value": ...} or an {"and": [...]} / {"or": [...]} group of conditions and groups (nestable). Operators: contains, eq, greater_than, greater_than_or_equal, ilike, in, is_distinct_from, is_nil, is_not_distinct_from, less_than, less_than_or_equal, like, not_eq, string_ends_with, string_starts_with. For 'is_nil' the value is true or false; for 'in' the value is an array. Fields: id, last_message_at, last_message_author_id, inserted_at, user_a_id, user_b_id, last_message_body, unread?, other_handle, event_payload.
offsetNoThe number of records to skip
contextYesExplain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. Never include personal data, such as names, email addresses or message text; refer to people by role, such as "the user" or "a buyer".
result_typeNoThe type of result to returnrun_query

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. Never include personal data, such as names, email addresses or message text; refer to people by role, such as \"the user\" or \"a buyer\".",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[]New value: +[
+  "context"
+]
  2. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds real behavioral value by stating the default ordering (most recent first) and, with no output schema, disclosing each row's shape. The clarification that unread? means unread 'on the website' is a useful nuance an agent could not infer. It stops short of noting that filtering, sorting, or count/aggregate modes are available.

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?

One dense sentence, front-loaded with the scope ('signed-in user's conversations ... most recent first') before the field list. Every clause earns its place except the somewhat awkward inline backticked parentheticals, which read more like column notes than prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only listing tool with no output schema, covering the returned fields and default order is the important part, and that is done well. However, the schema exposes a nested filter grammar and a result_type switch (count, exists, aggregate), and the description never signals that these exist, so an agent might run a full query where a count would do.

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 83%, so the baseline is 3 and the description is not obliged to re-document parameters. It does implicitly describe the default sort via 'most recent first', but says nothing about sort overrides, filter, limit/offset paging, or the result_type run_query/count/exists and aggregate modes, leaving the tool's querying power entirely to the schema.

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 names the exact resource (the signed-in user's conversations with other people) and enumerates the returned fields — other_handle, newest message, sent time, and unread? — so an agent knows precisely what comes back. The verb is implicit (it reads as a noun phrase describing a result set rather than saying 'list'/'return'), and it never contrasts itself with read_messages, which is the obvious adjacent sibling.

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 only implied: the 'signed-in user' scoping and 'most recent first' default tell an agent this is a personal inbox-overview read, and the mention of 'its newest message' hints it is for triage rather than reading a thread. There is no explicit statement of when to call this versus read_messages, nor any prerequisite or exclusion.

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

All Moatless toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources