Skip to main content
Glama
Canvas LMS MCP – Remote Edition

Canvas LMS MCP – Remote Edition

Post Entry

post_entry
Destructive

Posts a new top-level entry to a course discussion, visible to the whole class, with a preview and confirmation step before publishing.

Instructions

Post a new top-level entry to a course discussion. Visible to the whole class. Use reply_to_entry to answer someone's entry. [NEEDS CONFIRMATION: call it once for a preview and a confirm_token, show the preview to the user, and only if they say yes call it again with the same arguments, confirm=true and that confirm_token. Apps that can ask the user directly show a confirmation instead.]

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": {
      "course_id": "<course_id>",
      "topic_id": "<topic_id>",
      "message": "<message>"
    },
    "name": "post_entry"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoSet to true together with confirm_token to carry out a request you already previewed.
messageYesMessage text. Plain text or simple HTML.
topic_idYesDiscussion topic ID (numeric string). Get it from list_topics.
course_idYesCanvas course ID, a numeric string such as "12345". Get it from list_courses.
confirm_tokenNoThe one-time token from the preview. Only use it after the user has said yes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.0
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to actually execute. Omit or set false to get a dry-run preview first."New value: +"Set to true together with confirm_token to carry out a request you already previewed."
    • addedInput schema / properties / confirm_token
      Added value: +{
      +  "description": "The one-time token from the preview. Only use it after the user has said yes.",
      +  "type": "string"
      +}
  2. Changed3 schema fields changedv1.1.3
    • changedInput schema / properties / course_id / description
      Previous value: -"Canvas course ID"New value: +"Canvas course ID, a numeric string such as \"12345\". Get it from list_courses."
    • addedInput schema / properties / message / description
      Added value: +"Message text. Plain text or simple HTML."
    • changedInput schema / properties / topic_id / description
      Previous value: -"Canvas ID (numeric string)"New value: +"Discussion topic ID (numeric string). Get it from list_topics."
  3. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=true), the description discloses the audience ('Visible to the whole class') and the two-call preview/confirm_token protocol, including the fallback for apps that can ask the user directly. That is meaningful behavioral context the annotations cannot express. It stops short of saying whether the posted entry can later be edited or removed (edit_my_entry/delete_my_entry exist) or what the preview contains, which keeps it below 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 purpose and audience are front-loaded and the sibling routing follows sensibly, but the bracketed confirmation block is dense and reads as an internal annotation dropped into user-facing text. The confirm/confirm_token mechanics also restate much of what the schema fields already say, so the description is longer than it needs to be.

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?

For a write tool with no output schema, the description covers the essentials an agent needs to call it safely: audience, scope, sibling routing, and the mandatory confirmation handshake. It is missing expected return shape and any statement about post-publication editability, which are the remaining gaps for a destructive, non-idempotent operation.

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 baseline is 3; the description still adds the relational semantics of confirm and confirm_token — that the second call must repeat the same arguments and pair confirm=true with the token from the preview. It adds no guidance on message formatting or ID sourcing beyond what the schema already spells out.

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 gives a specific verb and resource ('Post a new top-level entry to a course discussion') and explicitly scopes it as top-level rather than a reply, naming 'reply_to_entry' as the contrasting sibling. An agent can distinguish this from reply_to_entry, edit_my_entry, and post_group_discussion without opening a schema.

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?

It states when to use the sibling instead ('Use reply_to_entry to answer someone's entry') and lays out a concrete conditional procedure: preview first, show the preview, and re-call only after explicit user assent. The when-not condition and the human-in-the-loop gating are both explicit rather than implied.

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