Skip to main content
Glama

Playbook

by com.playbook
OverviewDiscussionsAdmin

Create upload URL

create_upload_url

Step 1 of 2 for uploading a file you already HOLD — one generated locally, returned as base64 by an image API, or sitting on disk. Returns a one-time address to send the bytes to, plus the exact HTTP requests to make; the caller sends the bytes and finish_upload then turns them into an asset. Requires a token with the write scope and a caller that can make HTTP requests. Prefer upload_from_url whenever the file is already at a URL Playbook can fetch — that route is one call and needs nothing from you. Come here when it is not: no URL at all, a URL behind a login, an expired signed URL, a host that blocks datacenter addresses, or an ingest that failed with "Source URL too large to fetch; upload manually" (Playbook's fetcher runs to a five-minute streaming budget, which this path does not have — though it has a size ceiling of its own, below). When neither a reachable URL nor HTTP requests are available, share_board with enable_uploads returns a link a person can drop the file on. Files above 104857600 bytes are refused: these tools transfer in a single request, and splitting a larger file into chunks is what the Playbook web and desktop apps are for.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sizeYesExact size of the file in BYTES. It is checked against the workspace's storage allowance before the upload address is issued, and a wrong value here produces a signature that does not match the bytes you actually send. Measure it, do not estimate it.
filenameYesFilename including its extension, e.g. "moon.png". Playbook derives the stored file extension from it, so a name with no extension produces an object with no usable type. It does NOT become the asset's title — the two calls share no state, so pass the title again to finish_upload.
media_typeYesMIME type of the file, e.g. "image/png". Required, and required again at completion: it is covered by the upload signature, so the value you give here is the exact Content-Type the recipe will tell you to send. Get it from whatever produced the file rather than guessing from the extension.
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: -[
-  "filename",
-  "size",
-  "media_type",
-  "context"
-]New value: +[
+  "filename",
+  "size",
+  "media_type"
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: requires a token with the `write` scope, requires a caller capable of making HTTP requests, returns a one-time address, and enforces a hard 104857600-byte ceiling with an explanation (single-request transfer). It also contrasts Playbook's five-minute streaming fetcher budget against this path's lack of it. This is rich, non-obvious behavioral disclosure.

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?

Purpose is front-loaded ('Step 1 of 2...'), then the preference and fallback routing follow. It is long and dense, but nearly every clause carries routing or constraint information, so little is wasted; a slightly tighter phrasing would reach 5.

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 no output schema, the description still explains what comes back (a one-time address plus exact HTTP requests to make) and how the two-call flow completes. Combined with full schema coverage and the annotations, an agent has everything needed to invoke this 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 the schema already documents all four parameters, setting the baseline at 3. The description adds the 104857600-byte ceiling that constrains the `size` parameter and reinforces the cross-call state (title must be re-passed to finish_upload), giving modest value beyond 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+resource and frames it as 'Step 1 of 2 for uploading a file you already HOLD', immediately distinguishing it from the fetch-based sibling upload_from_url and from finish_upload. An agent can tell exactly what this produces: a one-time address plus the HTTP requests to send.

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 routes the agent: 'Prefer upload_from_url whenever the file is already at a URL', then enumerates the exact conditions that select this tool instead (no URL, URL behind a login, expired signed URL, blocked host, failed ingest), and names share_board with enable_uploads as the fallback when neither route is available. When-to-use, when-not, and alternatives are all covered.

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