Retrieve the connected Canvas account profile to view your user details; optionally return unmodified Canvas JSON with UTC times and HTML.
Read the connected Canvas profile (your Canvas account). For this connector's own version use canvas_connector_version.
| Name | Required | Description | Default |
|---|---|---|---|
| raw | No | true: Canvas's unmodified JSON (UTC times, HTML). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered without the description's help. The description adds no behavior beyond that — no mention of auth prerequisites, error behavior when no Canvas account is connected, or what the profile object contains. The parenthetical 'your Canvas account' is the only semantic addition, confirming this is caller-scoped.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with zero padding. The core read is front-loaded and the disambiguation against the connector-version sibling follows immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter read with annotations that already convey safety and idempotency, this is close to sufficient. The remaining gap is that no output schema exists and the description doesn't indicate which profile fields come back, leaving the agent to discover the return shape at call time.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
One optional parameter, but schema description coverage is 100% and it already explains 'raw' as unmodified JSON with UTC times and HTML. The description adds nothing about the flag, so the minimum-viable baseline of 3 is correct when the schema does all the work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
A specific verb ('Read') and resource ('the connected Canvas profile'), clarified parenthetically as the caller's own Canvas account. It explicitly carves out the connector-version case, though it does not distinguish itself from the sibling canvas_user, which likely covers other/arbitrary users.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clear context: use this for the authenticated account's profile, and it names the alternative (canvas_connector_version) for the connector's own version, which is the obvious confusion point. No exclusion guidance against canvas_user or canvas_enrollments, so it stops short of the top band.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.