Mark

Search Assets

search_assets

Read-onlyIdempotent

Searches the media library (images, video, documents) by text, type, source or Google Drive folder, newest first without text. Reaches the first 50 matches across all pages; capped is true when a page reached that limit and more may exist, so narrow with q, kind, source or folder. Does not change anything. Related: get_asset, add_asset, list_asset_folders.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_assets"
  }
}

Input Schema

Name	Required	Description
`q`	No	Name search. Typo-tolerant.
`kind`	No	Filter by kind.
`limit`	No	How many rows to return. Default 20, max 100.
`cursor`	No	Opaque cursor from a previous call's nextCursor.
`folder`	No	A Google Drive folder path from list_asset_folders. Matches that folder and its subfolders, exact and case-sensitive.
`source`	No	How the asset entered Mark.

Output Schema

Name	Required	Description	Default
`more`	Yes
`items`	Yes
`capped`	Yes
`nextCursor`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 29, 2026

addedInput schema / properties / folder

Added value: +{
+  "description": "A Google Drive folder path from list_asset_folders. Matches that folder and its subfolders, exact and case-sensitive.",
+  "type": "string"
+}

addedOutput schema / properties / capped
```
Added value: +{
+  "type": "boolean"
+}
```

changedOutput schema / required

Previous value: -[
-  "items",
-  "more",
-  "nextCursor"
-]New value: +[
+  "items",
+  "more",
+  "nextCursor",
+  "capped"
+]

First observedOct 1, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so 'Does not change anything' is mostly redundant. What earns credit is the disclosure of a non-obvious behavioral limit: only the first 50 matches are reachable across all pages, and the capped flag signals truncation — an agent would otherwise silently miss results.

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?

Two tight sentences with the capability and the 50-match cap front-loaded before the sibling pointers. The phrase 'newest first without text' is slightly compressed but the overall density is appropriate; nothing is padded.

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?

With an output schema present, return values need not be described, and the description still covers the one output detail that matters (the capped flag) plus the truncation limit. For a six-parameter, all-optional search tool this is fully sufficient.

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 the baseline is 3. The description adds value by grouping the four narrowing parameters (q, kind, source, folder) as the remedy for a capped result, and by noting default ordering is newest-first when no text query is given — neither of which is in the schema.

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 (searches the media library of images, video, documents) plus the filterable dimensions. The closing 'Related: get_asset, add_asset, list_asset_folders' makes it distinguishable from the sibling tools an agent might confuse it with.

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?

Gives explicit guidance on when results are incomplete ('capped is true ... so narrow with q, kind, source or folder') and names related siblings. It does not, however, contrast itself against search_cms_media or explain when a direct get_asset call is preferable to a search.

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

All Mark tools Inspect

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

Need Help?