Skip to main content
Glama
Sign In
Canvas LMS MCP Server

Canvas LMS MCP Server

by bruchris
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Get Conversation

get_conversation
Read-only

Retrieve a conversation's full message thread by ID to view subject, participants, and all messages, not just the summary. Calling this marks unread messages as read.

Instructions

Get one conversation's full message thread by id, returning its subject, participants, and every message (id, body, author_id, created_at) — not just the last_message summary list_conversations returns. Canvas marks any unread messages in this thread as read as a side effect of calling this, so re-reading a thread changes its unread state. Find the conversation_id with list_conversations. Use get_conversation_unread_count to check the inbox-wide unread total without marking anything read.

Input Schema

NameRequiredDescriptionDefault
conversation_idYesThe conversation ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.18.15
    • addedInput schema / properties / conversation_id / anyOf
      Added value: +[
+  {
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "pattern": "^[1-9][0-9]{0,18}$",
+    "type": "string"
+  }
+]
    • removedInput schema / properties / conversation_id / type
      Removed value: -"number"
  2. Changed1 schema field changedv1.18.11
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. First observedv1.18.0

TDQS

A4.9/5.0
Behavior5/5

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

The description discloses a non-obvious side effect that no structured field communicates: calling this marks unread messages in the thread as read, so re-reading mutates unread state. This is exactly the kind of hidden state-changing behavior an agent needs, and it is stated plainly rather than buried.

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

Conciseness5/5

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

Front-loaded with the core action and return contents, then the critical side-effect warning, then the discovery/alternative routing. Every clause carries new, load-bearing information with no filler.

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?

No output schema exists, yet the description fully specifies the return shape (subject, participants, full message list and each message's fields), plus the side effect and the id-discovery path. Nothing an agent needs to call this correctly 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 parameter itself is documented; the description adds the useful 'where to get it' pointer (find the conversation_id with list_conversations), which is meaning beyond the schema. But it does not describe the accepted id format (integer or numeric-string), leaving that entirely to the schema.

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?

Specific verb+resource: 'Get one conversation's full message thread by id.' It enumerates exactly what is returned (subject, participants, every message with id/body/author_id/created_at) and explicitly distinguishes itself from list_conversations ('not just the last_message summary'). An agent can never confuse this with the list variant.

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

Usage Guidelines5/5

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

Gives the prerequisite (find the conversation_id with list_conversations) and routes to the correct alternative for the unread-check use case (get_conversation_unread_count, explicitly 'without marking anything read'). This is genuine when/when-not/alternative guidance, not inference.

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

Deploy Server

Other Tools