Scribe Mail

Create an asset

create_asset

Upload an image to the workspace's asset library. Provide EITHER file_base64 (+ filename) OR source_url — exactly one. For a file the user uploaded in chat (no public URL), send its bytes as file_base64; if you cannot read the raw bytes on this platform, ask the user for a hosted URL or reuse an existing asset from list_assets instead of guessing. Non-images, bad base64, oversized files (>15MB), or a disallowed URL return 422.

Input Schema

Name	Required	Description
`name`	No	Display name (defaults to the filename).
`role`	No	Optional role: company_logo, profile_picture, or banner.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`filename`	No	Original filename (required when `file_base64` is given).
`source_url`	No	Public http(s) URL the server downloads the image from (alternative to file_base64). Redirects ARE followed (each hop re-checked); hosts resolving to private/loopback addresses are blocked. If a fetch fails (some hosts block server-side downloads), pass the bytes as `file_base64` instead.
`file_base64`	No	Base64-encoded image bytes. Provide WITH `filename`, or use `source_url` instead. A `data:` URI, line-wrapped base64, or base64url is accepted as-is — the server unwraps it, so pass whatever your file-reading helper returned without re-encoding.

Output Schema

Name	Required	Description	Default
`data`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 28, 2026
- removedOutput schema / properties / data / properties / name / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / data / properties / name / type
```
Added value: +[
+  "string",
+  "null"
+]
```
First observedOct 16, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare it as a non-read-only, non-destructive, non-idempotent, open-world write, so the safety profile is covered. The description adds real behavioral context annotations cannot: the 15MB size ceiling, the 422 failure class (non-image, bad base64, disallowed URL), and the practical advice to fall back to a different input mode when fetching fails. Not a 5 only because retry/duplicate-upload semantics (relevant given idempotentHint=false) are not addressed.

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?

Four sentences, front-loaded with the action, then the input rule, then the fallback, then the failure modes. Every sentence carries information; the fallback clause ("ask the user for a hosted URL or reuse an existing asset from list_assets instead of guessing") is slightly dense but still earns its place.

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 the description needn't explain returns, and annotations cover safety. What remains — what to upload, how to supply it, which fallback to take, and what causes a 422 — is all covered, so an agent could call this correctly on the first try.

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 the cross-parameter exclusivity rule and the filename-with-base64 coupling in one readable statement, plus the reassurance that data: URIs, base64url, and line-wrapped base64 are accepted without re-encoding. That last point is a genuine usability detail beyond the schema text.

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 ("Upload an image to the workspace's asset library") and scopes it to images only, which separates it from list_assets, update_asset, and delete_asset. An agent knows exactly what operation this performs before opening the 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?

Explicitly states the mutual-exclusion rule ("Provide EITHER `file_base64` (+ `filename`) OR `source_url` — exactly one") and gives a decision path for the common case: use bytes for chat-uploaded files, and fall back to asking the user for a hosted URL or reusing an existing asset via list_assets rather than guessing. This names both the condition and the alternative tool.

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

All Scribe Mail 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.