Skip to main content
Glama

Organize with AI (OwAI)

Export a collection or group

export_media

Export a collection or group using the app's shared export path. Local-folder and Apple Photos copies go to a unique directory on the owning device; Photos exports its current JPEG/MP4 rendering. OneDrive exports go to OneDrive/OwAI without requiring a desktop and remain pending until provider copying finishes. No originals or previous exports are overwritten. The completed result includes exported/failed counts and itemized outcomes. Local paths are not assistant attachments. Use an idempotency_key when retrying.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "selection_type": "<selection_type>",
      "selection_id": "<selection_id>"
    },
    "name": "export_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
selection_idYes
watermark_idNo
selection_typeYes
idempotency_keyNo

Output Schema

NameRequiredDescriptionDefault
commandYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / watermark_id
      Added value: +{
      +  "exclusiveMinimum": 0,
      +  "maximum": 9007199254740991,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / command / properties / attempt / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / command / properties / attempt / minimum
      Added value: +0
    • changedOutput schema / properties / command / properties / attempt / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / command / properties / claimed_at / anyOf
      Added value: +[
      +  {
      +    "maximum": 9007199254740991,
      +    "minimum": 0,
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / command / properties / claimed_at / type
      Removed value: -[
      -  "number",
      -  "null"
      -]
    • addedOutput schema / properties / command / properties / completed_at / anyOf
      Added value: +[
      +  {
      +    "maximum": 9007199254740991,
      +    "minimum": 0,
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / command / properties / completed_at / type
      Removed value: -[
      -  "number",
      -  "null"
      -]
    • addedOutput schema / properties / command / properties / requested_at / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / command / properties / requested_at / minimum
      Added value: +0
    • changedOutput schema / properties / command / properties / requested_at / type
      Previous value: -"number"New value: +"integer"
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish this is a non-read, non-destructive mutation, and the description adds real value beyond them: exports go to a unique directory per owning device, OneDrive exports stay pending until provider copying finishes, and no originals or previous exports are overwritten. The async/pending semantics and the no-overwrite guarantee are exactly the kind of traits annotations cannot express.

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?

The purpose is front-loaded in the first clause and each following sentence adds a distinct fact (destination behavior, pending state, safety guarantee, retry guidance). The paragraph is dense but no sentence is filler, though it could be broken into a short list for faster scanning.

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?

For a mutation tool with annotations and an output schema, the description covers the essential traits: destination routing, asynchronous completion, non-destructive overwrite policy, and retry semantics. The remaining gap is that it does not document watermark_id or the meaning of selection_id, which a caller must still infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across four parameters, so the description must carry the meaning. It explains idempotency_key's retry role and implicitly ties the collection/group wording to selection_type, but watermark_id is never mentioned and selection_id is never defined, leaving half the surface undocumented.

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 ("Export a collection or group") and is the only export tool among siblings, so it is trivially distinguishable from inspect_*/manage_*/read_* tools. The addition of "using the app's shared export path" pins down scope further.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives behavioral context for destinations and a conditional instruction ("Use an idempotency_key when retrying"), which is genuine usage guidance. However, it never states when to choose export versus a sibling like locate_media or preview_media_deletion, nor does it state prerequisites, so usage is mostly implied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources