Skip to main content
Glama

Bernuvia

by com.bernuvia
OverviewDiscussionsAdmin

my_draft

Returns the saved publish draft (there is ONE per account, shared with the /vender assistant) and what it still needs before it can be submitted: missing is the result of the SAME validation the submission runs, so with readyToSubmit: true all that is left is uploading the ZIP and calling submit_for_review. It comes back in the same vocabulary create_draft and update_draft accept: prices as a number and licence standard or exclusive; video carries the state of its native video (queued, processing, ready or failed with its reason).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
draftNoThe draft in the MCP vocabulary (the same fields as create_draft).
videoNoThe template video and its processing state; null when there is none. It can be submitted while it is queued or processing, but the human review only approves it when it is ready.
editingNoSlug the draft edits, or null if it is for a new template.
missingYesFields the listing is still missing before it can be submitted.
savedAtNoWhen it was last saved (ISO 8601).
hasDraftYesThere is a draft saved on the account.
nextStepYesWhat to do now, in one sentence.
readyToSubmitYesThe listing already passes the submission validation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / video
      Added value: +{
+  "additionalProperties": true,
+  "description": "The template video and its processing state; null when there is none. It can be submitted while it is queued or processing, but the human review only approves it when it is ready.",
+  "properties": {
+    "durationSeconds": {
+      "description": "Length in seconds, only when ready.",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "error": {
+      "description": "With failed: format, no_video, too_long, too_large, dimensions, codec, corrupt, missing, timeout or internal.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "height": {
+      "description": "Height of the MP4 in pixels, only when ready.",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "path": {
+      "description": "The stored path (the one that goes in `video`).",
+      "type": "string"
+    },
+    "poster": {
+      "description": "Absolute address of its still cover (WebP), only when ready.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "reason": {
+      "description": "The same reason in plain words.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "description": "awaiting_upload (the server has not seen the file yet: it is queued as soon as a listing or draft that names it is saved), queued, processing, ready or failed.",
+      "type": "string"
+    },
+    "url": {
+      "description": "Absolute address of the processed MP4, only when ready.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "width": {
+      "description": "Width of the MP4 in pixels, only when ready.",
+      "type": [
+        "number",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "path",
+    "status",
+    "error",
+    "reason",
+    "url",
+    "poster",
+    "width",
+    "height",
+    "durationSeconds"
+  ],
+  "type": [
+    "object",
+    "null"
+  ]
+}
  2. Changed7 schema fields changed
    • changedOutput schema / properties / draft / description
      Previous value: -"El borrador en el vocabulario del MCP (los mismos campos que create_draft)."New value: +"The draft in the MCP vocabulary (the same fields as create_draft)."
    • changedOutput schema / properties / editing / description
      Previous value: -"Slug que edita el borrador, o null si es de una plantilla nueva."New value: +"Slug the draft edits, or null if it is for a new template."
    • changedOutput schema / properties / hasDraft / description
      Previous value: -"Hay un borrador guardado en la cuenta."New value: +"There is a draft saved on the account."
    • changedOutput schema / properties / missing / description
      Previous value: -"Campos que le faltan a la ficha para poder enviarse."New value: +"Fields the listing is still missing before it can be submitted."
    • changedOutput schema / properties / nextStep / description
      Previous value: -"Qué hacer ahora, en una frase."New value: +"What to do now, in one sentence."
    • changedOutput schema / properties / readyToSubmit / description
      Previous value: -"La ficha pasa ya la validación del envío."New value: +"The listing already passes the submission validation."
    • changedOutput schema / properties / savedAt / description
      Previous value: -"Cuándo se guardó por última vez (ISO 8601)."New value: +"When it was last saved (ISO 8601)."
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses the one-draft-per-account constraint, that `missing` is the SAME validation the submission runs, the readyToSubmit semantics, and the video state machine (queued, processing, ready, failed with reason). These are substantive behavioral traits an agent needs to act correctly.

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-loaded with the core purpose in the opening clause, followed by actionable detail. It is dense with nested parentheticals but each clause earns its place; only mild run-on density keeps it from a 5.

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?

An output schema exists, so the description need not explain return values, yet it adds interpretive context (validation provenance, video states, vocabulary alignment). Behavior, constraints, and next-step workflow are all covered, leaving little an agent would need beyond the 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?

Zero parameters, so the baseline is 4. The description instead documents the return vocabulary (prices as numbers, licence standard/exclusive, video state), which is output semantics rather than parameter semantics, but it usefully aligns the response with what create_draft/update_draft accept.

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 (Returns) and resource (the saved publish draft), plus scope: there is exactly ONE per account, shared with the /vender assistant. This clearly distinguishes it from the create_draft, update_draft, and delete_draft siblings by making its read-only retrieval nature explicit.

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?

Implies usage through the submit workflow: with readyToSubmit: true, 'all that is left is uploading the ZIP and calling submit_for_review.' This routes the agent to the next step, though it never explicitly states when NOT to use it or names an alternative retrieval path.

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

All Bernuvia 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