AskEditor

Start file upload

create_upload

[write] Open an upload of a local file (video, image or audio, up to 4 GB) and sign a URL for each part. Use for a file on your machine: PUT each part to its url, keep each ETag, then complete_upload. For parts past the first 50, or after 15 minutes, call again with upload_id and part_numbers. Not for a web address (use import_media_from_url). Returns upload_id, part_size, part_count, parts [{part_number, url}], how (a shell recipe) and next_part_numbers when more remain. Related: complete_upload, import_media_from_url, list_media. Full docs: load_skill with tools: [name].

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": {
      "project_id": "<project_id>"
    },
    "name": "create_upload"
  }
}

Input Schema

Name	Required	Description
`bytes`	No	Exact size in bytes. To open an upload.
`items`	No	Many files at once, max 8, each with this tool's fields; fields beside it are defaults.
`filename`	No	The file's name, e.g. talk.mp4. To open an upload.
`upload_id`	No	An open upload's id, to sign more of its parts instead of opening a new one.
`project_id`	Yes	The AskEditor project this acts on (from list_projects).
`content_type`	No	Its type (default read from the filename's extension).
`part_numbers`	No	1-based parts to sign (default the first 50).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly=false and destructive=false, and the description layers on significantly more: the 15-minute signing window, the 50-part cap, the obligation to PUT each part and retain ETags, and the required completion via complete_upload. It also enumerates the return payload, which the tool otherwise lacks an output schema for.

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 write action and the local-file constraint before the alternative and the return shape. It is dense but nearly every clause carries operational weight; the trailing 'Related' and 'Full docs' pointers are minor padding but help routing and progressive disclosure.

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 7-parameter mutation tool with no output schema, the description supplies the missing return contract (upload_id, part_size, part_count, parts, next_part_numbers) and the multi-step protocol ending in complete_upload. An agent can complete a correct call sequence from the description alone.

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 workflow meaning the schema does not: upload_id is for re-signing parts of an existing upload rather than opening a new one, and part_numbers governs parts beyond the initial 50. The only gap is that `items` (batch of up to 8 files) is not mentioned in the description at all.

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 ('Open an upload of a local file ... and sign a URL for each part') with concrete scope (video/image/audio, up to 4 GB). It explicitly distinguishes itself from the nearest sibling by excluding web addresses and naming import_media_from_url.

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 the when ('a file on your machine'), the when-not ('Not for a web address'), the explicit alternative (import_media_from_url), and the resumption condition ('parts past the first 50, or after 15 minutes, call again with upload_id and part_numbers'). Nothing about tool selection is left to inference.

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

All AskEditor 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.

Resources

Need Help?