Skip to main content
Glama
Sign In

Canva

by com.canva.mcp
OverviewDiscussionsAdmin

Get Separate Image Layers Job

get-separate-image-layers-job
Read-only

Check the status and result of an image layer-separation job started by separate-image-layers.

Only call with the job_id and continuation_token from the most recent separate-image-layers or get-separate-image-layers-job response, and never before polling_policy.wait_seconds have elapsed. This is an internal lifecycle tool, not a user-selectable action.

Returns the job's current status and, once completed, the new design with the url to share with the user.

Input Schema

NameRequiredDescriptionDefault
job_idYesStable ID of the layer-separation job, returned when the separation request starts.
user_intentNoMandatory description of what the user is trying to accomplish with this tool call. This should always be provided by LLM clients. Please keep it concise (255 characters or less recommended).
continuation_tokenYesExact continuation token returned by the most recent response for this layer-separation job.

Output Schema

NameRequiredDescriptionDefault
designNoThe created design. Only present when the job completed.
job_idNoID of the separation job. Stable across all responses.
statusYesStatus of the job. While 'in_progress', poll again with the job_id and the continuation_token from this response. 'polled_too_early' means the wait window had not elapsed and nothing was checked. 'completed' carries the design; 'failed' carries the failure.
failureNoWhy the job failed. Only present when status is 'failed'.
polling_policyNoHow and when to poll next. Only present while the job is still running.
continuation_tokenNoOpaque token to pass on the next poll. Always use the most recent token from the last response. Absent once the job is finished.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedOutput schema / properties / failure / properties / code / description
      Previous value: -"Why the job failed. 'moderation_blocked' means the image was declined by content moderation - tell the user and do not retry the same image. 'quota_exceeded' means the user is out of AI credits. 'throttled' means too many requests - retry later. 'invalid_input' will not succeed on retry with the same image."New value: +"Why the job failed. 'moderation_blocked' means the image was declined by content moderation - tell the user and do not retry the same image. 'quota_exceeded' means the user is out of AI credits. 'throttled' means too many requests - retry later. 'invalid_input' will not succeed on retry with the same image. 'job_expired' means the result was not collected in time and no design was saved - start a new separate-image-layers request."
    • changedOutput schema / properties / failure / properties / code / enum
      Previous value: -[
-  "moderation_blocked",
-  "quota_exceeded",
-  "throttled",
-  "invalid_input",
-  "internal_error"
-]New value: +[
+  "moderation_blocked",
+  "quota_exceeded",
+  "throttled",
+  "invalid_input",
+  "job_expired",
+  "internal_error"
+]
  2. Added

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: the polling backoff requirement and the fact that the URL only appears once the job completes. It could go further on failure states or expiry of tokens, but it is well above the annotation baseline.

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?

Three tight sentences ordered by importance: what it does, how to call it safely, what comes back. No filler, and the lifecycle caveat is placed before the return-value detail.

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?

An output schema exists, so return shape need not be enumerated, yet the description still summarizes the completed payload (new design plus share URL). Combined with the polling rule and token provenance, an agent has everything needed to poll this job correctly.

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 all three parameters are documented in-schema, giving a baseline of 3. The description adds provenance semantics the schema does not convey — that continuation_token must be the exact token from the most recent response of this specific job. It does not mention user_intent, but that is a generic client-supplied field.

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 (check) and resource (image layer-separation job), and explicitly ties the tool to its producer, separate-image-layers. This distinguishes it cleanly from the adjacent job-status siblings (get-generate-image-job, get-create-design-async-job, get-video-generation-status).

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?

Explicitly constrains invocation: only with the job_id and continuation_token from the most recent separate-image-layers or get-separate-image-layers-job response, and never before polling_policy.wait_seconds have elapsed. It also declares the tool is an internal lifecycle tool rather than a user-selectable action, which is exactly the when-not guidance an agent needs.

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

All Canva toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources