Skip to main content
Glama

Playbook

by com.playbook
OverviewDiscussionsAdmin

Get asset previews

get_asset_previews
Read-only

Render one or more assets as images at a size you choose, and get a URL per asset. This is how you LOOK at Playbook assets: the display_url on an asset is the full-size render (5000px is normal), which is wasteful to fetch and too large for most vision models. Ask for 1024 wide and you get a 1024px image. The URLs are SHORT-LIVED — they die at the end of the next hour, so 1-2 hours depending on when you call. They suit fetching now or showing in the current reply; anything that must keep working later — a stored link, a document, a hand-off — needs get_asset_permalinks. A SIZE IS REQUIRED — pass width, height, or both; without one this would hand back the same full-size render you already have. IMAGES ONLY: it renders the asset's original file, so a video or a PDF comes back with a URL that will not load, and an asset with no file at all (a note, a colour swatch, a link) is listed under no_file_to_render rather than given a URL. Check media_type starts with image/ first. Tokens missing from the response entirely are under not_found — unknown, or not visible to this token. One render per token per call, so ask for the assets you actually need to see rather than a whole board.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
widthNoWidth in pixels. 1024 is plenty for a vision model; pass width alone to keep the aspect ratio
formatNoOutput format. Omit to keep the original — pass jpeg when the consumer is picky about webp
heightNoHeight in pixels
asset_tokensYesTokens of the IMAGE assets to render (max 100 per call)
organizationNoWorkspace slug, as returned by list_organizations. Omit it when the account has a single workspace — it is then resolved from your token. Pass it only when the account has several, or when you mean a workspace other than the obvious one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / context
      Removed value: -{
-  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "asset_tokens",
-  "context"
-]New value: +[
+  "asset_tokens"
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safety profile (readOnly, non-destructive, not open-world). The description adds rich behavior beyond that: URLs are short-lived (~1-2 hours), a size is mandatory or you get the full render back, non-image assets return URLs that won't load, no-file assets land in no_file_to_render, unknown/invisible tokens land in not_found, and one render per token per call.

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-loads the core purpose, then the size requirement and image-only constraint, so the agent hits the critical rules early. It is long and heavy on caps emphasis, with a couple of sentences that could be tightened, but nearly every line carries a distinct constraint.

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 a 5-param tool with no output schema, the description compensates by naming the response buckets (no_file_to_render, not_found, URL-per-asset) and the size/format/media constraints. An agent has enough to call it correctly and interpret the result without an output schema.

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, but the description adds cross-parameter meaning the schema cannot: why width/height must be supplied (otherwise the same full-size render), and the token-visibility semantics behind not_found. It stops short of adding format or organization guidance beyond what the schema already carries.

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+resource ('Render one or more assets as images... get a URL per asset') and explicitly distinguishes itself from the full-size display_url render and from get_asset_permalinks. An agent can tell it apart from get_asset and get_asset_permalinks without opening any schema.

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 ('This is how you LOOK at Playbook assets'), when-not ('wasteful to fetch and too large for most vision models'), and the alternative for durable links ('anything that must keep working later... needs get_asset_permalinks'). It also states the pre-condition (check media_type starts with image/).

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

All Playbook 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