Skip to main content
Glama
Sign In

Canva

by com.canva.mcp
OverviewDiscussionsAdmin

Search Designs

search-designs
Read-only

Locate or browse the user's existing Canva designs. Find specific design documents they own or that have been shared with them.

Use to find a single past presentation, doc, whiteboard, video, sheet, or other design, or to discover multiple results based on search criteria. Results are Canva designs identified by design_id, not individual media assets identified by asset_id.

Not for locating reusable templates or individual uploaded or generated media assets.

Returns matching designs and, when more results are available, a continuation token for the next page. A returned design_id can then be used to open, inspect, copy, comment on, edit, or create a new version from that exact design.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of designs to return.
queryNoOptional text to match against a design's title or content. Use the user's keywords, such as a project name, topic, or phrase. If supplied, "sort_by" must be "relevance".
sort_byNoHow to order results. Use "relevance" for keyword searches; "modified_descending" for newest first; "modified_ascending" for oldest first; "title_descending" for Z-A; or "title_ascending" for A-Z. Omit to use "relevance".
ownershipNoWhose designs to search. Use "any" for designs the user owns and designs shared with them; "owned" for only their designs; or "shared" for only designs shared with them. Omit to use "any".
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).
continuationNoThe exact token returned by the previous search with the same query, filters, and sort order. Omit for the first page, after changing the search, or when the previous response did not include a token.
design_typesNoOptional design types to include. A design is returned if it matches any supplied type. Currently, only "presentation" is supported.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / continuation / description
      Previous value: -"\n            Pagination token for the current search context.\n\n            CRITICAL RULES:\n            - ONLY set this parameter if the previous response included a continuation token.\n            - If no continuation token was returned → OMIT this parameter completely. NEVER EVER fabricate a token.\n            - Do not set to null, empty string, or any other value when no token was provided.\n\n            Usage:\n            - First request: omit this parameter\n            - Previous response had continuation token: use that exact token\n            - Previous response had NO continuation token: omit this parameter\n            - New search query: omit this parameter\n          "New value: +"The exact token returned by the previous search with the same query, filters, and sort order. Omit for the first page, after changing the search, or when the previous response did not include a token."
    • changedInput schema / properties / design_types / description
      Previous value: -"Filter designs by design type; a design is returned if it matches any of the given types. Currently only 'presentation' is supported."New value: +"Optional design types to include. A design is returned if it matches any supplied type. Currently, only \"presentation\" is supported."
    • changedInput schema / properties / ownership / description
      Previous value: -"Filter designs by ownership: 'any' for all designs owned by and shared with you (default), 'owned' for designs you created, 'shared' for designs shared with you"New value: +"Whose designs to search. Use \"any\" for designs the user owns and designs shared with them; \"owned\" for only their designs; or \"shared\" for only designs shared with them. Omit to use \"any\"."
    • changedInput schema / properties / query / description
      Previous value: -"Optional search term to filter designs by title or content. If it is used, 'sortBy' must be set to 'relevance'."New value: +"Optional text to match against a design's title or content. Use the user's keywords, such as a project name, topic, or phrase. If supplied, \"sort_by\" must be \"relevance\"."
    • changedInput schema / properties / sort_by / description
      Previous value: -"Sort results by: 'relevance' (default), 'modified_descending' (newest first), 'modified_ascending' (oldest first), 'title_descending' (Z-A), 'title_ascending' (A-Z). Optional sort order for results. If 'query' is used, 'sortBy' must be set to 'relevance'."New value: +"How to order results. Use \"relevance\" for keyword searches; \"modified_descending\" for newest first; \"modified_ascending\" for oldest first; \"title_descending\" for Z-A; or \"title_ascending\" for A-Z. Omit to use \"relevance\"."
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare read-only, non-destructive, closed-world behavior. The description adds useful context beyond that: it explains the return format (matching designs plus a continuation token for pagination) and how the returned design_id can be used for follow-up operations. It does not mention other behavioral traits like rate limits or required permissions, but for a read-only search those are less critical.

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?

The description is front-loaded with purpose and well-structured across four sentences. There is slight redundancy between 'Locate or browse the user's existing Canva designs' and 'Find specific design documents they own or that have been shared with them,' but overall it is efficient.

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?

Given the tool's complexity (7 parameters, no output schema) and the presence of annotations covering safety, the description is mostly complete. It covers purpose, exclusions, return format, and next steps with design_id. It could go slightly further by listing fields present in returned designs, but it provides enough for an agent to call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents all seven parameters, including enums for sort_by and ownership. The description adds only marginal meaning (e.g., design_id vs asset_id), so the baseline of 3 is appropriate.

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 uses specific verbs (locate, browse, find) with the resource (Canva designs) and explicitly distinguishes designs from media assets and templates. An agent can tell exactly what this tool returns and what it does not, without needing the sibling list.

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

Usage Guidelines4/5

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

It gives clear when-to-use guidance (find a single past design or discover multiple results based on search criteria) and explicit when-not-to-use guidance (not for templates or individual media assets). However, it does not name the specific sibling tools (e.g., search-brand-templates, get-assets) that should be used instead, leaving that inference to the agent.

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