Skip to main content
Glama

Raw Canvas Request

raw_canvas_request
Destructive

Use when no other tool covers your case: call a Canvas REST API endpoint under /api/v1 directly, with read-only GETs and confirm-gated POST, PUT and DELETE writes.

Instructions

Call a Canvas REST API endpoint directly, for anything the other tools don't cover. Requests only go to your Canvas, inside /api/v1. GET is read-only. POST, PUT and DELETE can change data: they are blocked when CANVAS_ALLOW_WRITES=false and need confirmation. Quiz-submission writes and endpoints that hand out sign-ins or tokens are always refused. [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": {
      "method": "<method>",
      "path": "<path>"
    },
    "name": "raw_canvas_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoJSON body for POST/PUT
pathYesAPI path after /api/v1, e.g. '/users/self/enrollments'
methodYesHTTP method
paramsNoQuery parameters
confirmNoSet to true together with confirm_token to carry out a request you already previewed.
paginateNoFollow Link headers and collect all pages (GET only)
max_itemsNoWith paginate=true, stop after this many items. Default 200.
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 changedv1.3.0
    • changedInput schema / properties / confirm / description
      Previous value: -"Required for POST/PUT/DELETE"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. Changed1 schema field changedv1.0.2
    • addedInput schema / properties / max_items / description
      Added value: +"With paginate=true, stop after this many items. Default 200."
  3. First observedv1.0.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and openWorldHint=true, but the description adds the specifics those hints cannot: confinement to the caller's own Canvas under /api/v1, read-only semantics for GET, write blocking via CANVAS_ALLOW_WRITES, and a hard refusal list. It also discloses the two-call confirm_token protocol, which is non-obvious behavior an agent could otherwise stumble into.

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?

Front-loaded with purpose, then safety constraints, then the confirmation procedure in a clearly bracketed block. Dense but every sentence carries operational weight; the parenthetical about apps showing their own confirmation is slightly tangential but explains a deviation the agent may observe.

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?

For an 8-parameter open-world escape hatch with no output schema, the definition covers the dangerous parts: scope of the endpoint space, write gating, permanently refused endpoints, and the exact confirmation handshake. Return-value format is not promised, but the description never claims to describe it and the underlying API is the contract.

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 per-parameter meaning is already documented and the baseline is 3. The description goes further by explaining the relationship between 'confirm' and 'confirm_token' (same arguments, second call with confirm=true) and by naming the path prefix constraint, adding real semantics the schema fields state only individually.

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?

States a specific verb and resource ('Call a Canvas REST API endpoint directly') and immediately scopes it as the fallback: 'for anything the other tools don't cover'. That single clause distinguishes it from the entire ~200-tool sibling list without requiring schema inspection.

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 explicit when-to-use (only when no other tool covers it), when-not (blocked when CANVAS_ALLOW_WRITES=false; always refused for quiz-submission writes and sign-in/token endpoints), and a concrete procedural alternative (preview first, then confirm). Nothing is left to inference about routing or gating.

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